Past Meetings

Date: Wed, September 28, 2016
Time: 7:00 pm
Location: The MITRE Corporation
Title: Social Physics 
Speaker: Professor Alex ‘Sandy’ Pentland, Massachusetts Institute of Technology
Abstract: Fine grain data about human behavior, harvested from cell phones, credit cards, cars, and similar sources, has given us new ways to quantify the dynamics and decision making in real-world situations  by use of heterogeneous stochastic network models. Social physics models of human behavior have generated successful predictions in domains ranging from finance, to  health, to transportation, to consumer consumption.  Experiments at scales from hundreds to millions of people will be described.  In order to safely harness these new capabilities a new more secure and privacy-preserving data architecture is required.  I will describe the Trusted Data architecture we have developed with support from the EU, and in collaboration with companies such at ATT, IBM, Intuit, in consulation with Treasury and Commerce.

Date: Wed, October 28, 2015
Time: 7:00 pm
Location: The MITRE Corporation
Title: Evaluating Quality of Topics Derived from Latent Dirichlet Allocation
Speaker: Vineet Mehta, PhD, The MITRE Corporation
Abstract: Recent years have witnessed a growing body of work in developing metrics and techniques for evaluating the quality of topic models and the topics they generate. This is particularly true for text data where significant attention has been given to the semantic interpretability of topics using measures such as coherence. It has been shown however that topic assessments based on coherence metrics do not always align well with human judgment. Other efforts have examined the utility of information-theoretic distance metrics for evaluating topic quality in connection with semantic interpretability. Although there has been progress in evaluating interpretability of topics, the existing intrinsic evaluation metrics do not address some of the other aspects of concern in topic modeling such as: the number of topics to select, the ability to align topics from different models, and assessing the quality of training data. Here we propose an alternative metric for characterizing topic quality that addresses all three aforementioned issues.

Date: Wed, April 8, 2015
Time: 7:00 pm
Location: The MITRE Corporation
Title: Predictive Modeling from Text using Fixed Length Vectors
Speaker: Steve Gallant, MultiModel Research
Abstract: This is an introductory overview of how to represent text (and images) for predictive analytics. Applications include Sentiment Analysis, classifying news stories or emails, building marketing models (acquisition, churn), and anomaly detection. The key technique is how to transform text (of varying length), as well as sentence or document structure, into a single, distributed, fixed-length vector. For example, we may want to change each news story into a list of exactly 500 numbers. The main reason to make this transformation is to enable machine learning approaches -- which require fixed-length vectors -- to construct predictive models. (Neural networks provide a motivation for this work.) We'll see a live demonstration classifying news stories over the web

Date: Tue, Feb 24, 2015
Time: 6:30 pm
Location: Bentley University
Title: Data Science for Workforce Optimization: Reducing Employee Attrition
Speaker: Pasha Roberts, Chief Scientist and Co-founder, Talent Analytics, Corp.
Abstract: Predictive methods are often seen in marketing, finance, and logistics. The use of these advanced methods for workforce analytics are an emerging and powerful domain for practice, with applications in talent selection, sourcing, training, development, planning and optimization. This presentation by Talent Analytics Chief Scientist Pasha Roberts will provide an overview of the advanced analytics field with a range of applications that are emerging in application to a company's largest and most important expense: their workers.

Date: Wed, Sept 24, 2014
Time: 6:30 pm
Location: Bentley University
Speaker: Vladimir Shnaydman, ORBee Consulting
Title: Strategic R&D project portfolio planning - approaches, techniques, tools
Abstract: Portfolio planning is critical for developing long-term company strategy. The goal is to select “right” portfolio of internal and external R&D projects for funding, align company strategy and limited resources, optimize resource utilization, and manage portfolio risk to buffer the organization against unfavorable events. Such factors as insufficient/uncertain data and each company’ unique business environment could contribute to the complexity of portfolio planning. It is also hard to validate modeling results due to a long planning horizon, and highly dynamic nature of business. Importance of portfolio planning and its complexity dictates application of advanced techniques based on Operations Research methodology. OR based portfolio planning models are much more efficient than most “simplistic” and sometimes inaccurate techniques.

Date: Tuesday, May 13, 2014
Time: 6:30 pm
Location: Massachusetts Institute of Technology
Speaker: Suzanne de Treville, Visiting Professor, MIT
Title: Valuing Lead Time
Abstract: When do short lead times warrant a cost premium? Decision makers have struggled to quantify the benefits of short lead times in spite of the general agreement that they enhance competitiveness. This lack of methodology has contributed to waves of offshoring that have extended supply chains. We use quantitative finance tools to understand the determinants of the marginal value of time. The value of lead time is lower when demand is sufficiently predictable to allow forecasting, salvage or residual values are high, and the firm sets service levels so as to maximize profit. When forecast evolution is unpredictable, salvage losses are considerable, and/or the service level is higher than that which maximizes profit, the value of time is often high enough to compensate for the cost of cutting lead time. We apply our model to three industrial cases, and show how it helped managers understand and quantify the value of time.

Date: Thursday, April 24, 2014
Time: 6:30 pm
Location: Bentley University
Speaker: Victor S.Y. Lo, Fidelity Investments and Bentley University
Title: Identifying Individuals Who Are Truly Impacted by Treatment: Introduction to and Recent Advances in Uplift Modeling
Abstract: Traditional randomized experiments allow us to determine the overall impact of a treatment program (marketing, medical, social, education, etc.). Uplift modeling (also known as true lift, net lift, incremental lift) takes a further step to identify individuals who are truly positively influenced by a treatment through data mining / statistical modeling / machine learning. This technique allows us to identify the “persuadables” and thus optimize target selection in order to maximize treatment benefits. This important subfield of data mining/data science/business analytics has gained a lot of attention in areas such as personalized marketing, personalized medicine, and political election with plenty of publications and presentations appeared in recent years from both industry practitioners and academics. In this talk, I will introduce the concept of Uplift, review existing methods, contrast with the traditional approach, and propose a new method that can be implemented with standard software. A method and metrics for model assessment will be recommended. Our discussion will include new approaches to handling a general situation where only observational data are available, i.e. without randomized experiments, using techniques from causal inference. Additionally, an integrated modeling approach for uplift and direct response (where it can be identified who actually responded, e.g., click-through or coupon scanning) will be discussed. While the talk is geared towards marketing applications (“personalized marketing”), the same methodologies can be readily applied in other fields such as insurance, medicine, education, and social programs.

Date: Wednesday, January 15, 2014
Time: 6:30 pm
Location: Northeastern University School of Pharmacy
Speaker: James C. Benneyan, Ph.D., Executive Director, Northeastern University Healthcare Systems Engineering Institute, College of Engineering, Bouve College of Health Sciences
Title: A Model for Scaling Healthcare Systems Engineering Nationally: The Medicare/Medicaid Innovation Center Demonstration Project
Abstract: The pace of healthcare improvement and innovation is frustratingly slow, at a time when improvement needs are increasingly urgent. Among other approaches, there recently has been renewed interest in greater application of industrial and systems engineering (ISyE), as used to improve efficiency, quality, and outcomes in other complex industries. While some health systems, funding organizations, and national academies are increasingly exploring ISyE, it remains largely unclear how to most effectively apply, expand, and sustain healthcare systems engineering for maximal impact nationally, at scale and near immediately. As one approach, this presentation will summarize the Centers for Medicare and Medicaid Services (CMS) $8 million demonstration project led by Northeastern University to develop a system of scalable healthcare systems engineering regional extension centers across the U.S. that significantly improves the triple aim of better health, better care, and lower costs. We will provide an overview of the project's motivation, operations, example projects, results-to-date, and criteria for additional health systems to participate.

Date: Wednesday, Nov 6, 2013
Speaker: Marta Gonzales, Massachusetts Institute of Technology Civil and Environmental Engineering Department Engineering System Division, Operations Research Center
Location: MIT
Title: Tackling Urban Challenges with Information and Communications Technologies
Abstract: Time scales differentiate human mobility. While the mechanism for longtime scales has been studied, the underlying mechanism on the daily scale is still unrevealed. Here, we uncover the mechanism responsible for the daily mobility patterns by analyzing the temporal and spatial trajectories of thousands of persons as individual networks. Using the concept of motifs from network theory, we find only 17 unique networks are present in daily mobility and they follow simple rules. These networks, called here motifs, are sufficient to capture up to 90 per cent of the population in surveys and mobile phone datasets for different countries. Each individual exhibits a characteristic motif, which seems to be stable over several months. Consequently, an analytically tractable framework for Markov chains can reproduce daily human mobility by modeling periods of high-frequency trips followed by periods of lower activity as the key ingredient. We show how this processed information from the data can be brought back to the urban system; as a case of study we focus on strategies to reduce congestion based on targeting most congested roads and the census tracks that are more exposed to the congestion.  

Date: October 23, 2013
Speaker: John Li, Managing Partner, Focus Optimal
Location: Bentley University, Center for Marketing Technology (CMT)
Title: Social media analytics - a case study of how to apply text mining to predict sentiment
Abstract: Twitter has become an increasingly important venue for consumers to express their opinions. Due to the sheer volume, it is not efficient (if possible at all) for customer service team to sort through every post to find the small fraction of negative posts that require follow-up. In this case, a classification model was developed to predict negative sentiment via text mining and machine learning. The model increased the concentration of posts with negative sentiment by 2.5 times over the baseline. The model drivers also provide insights on how past decisions may have contributed to high volume of customer dissatisfaction in social media.  

Date: June 18, 2013
Speaker: Jack Levis, Director of Process Management, UPS, and INFORMS Vice President of Practice Activities
Location: Verizon Labs
Title: INFORMS and Analytics Certification
Abstract: Would you like to see CAP (Certified Analytics Professional) after your name? You can make it happen on October 3 in Boston. INFORMS has decided to embrace and serve the analytics profession. The first major offering is analytics professional certification, which was offered for the first time on April 7, 2013, at INFORMS Conference on Business Analytics and Operations Research, San Antonio, Texas. Thirty-eight individuals have earned the CAP designation to date and set themselves apart. In his talk that will be accompanied by informative slides, Jack Levis, Vice President of Practice Activities at INFORMS, will cover what professional certification is and is not and why you should you be interested. He will cover the eligibility requirements and benefits of analytics certification for individuals, employers, and the profession in general. He will cover the nature of the exam, the rigorous job task analysis the exam is based on, and how you can prepare. Plenty of time will be left for Q and A to help you make your decision to pursue analytics certification. An analytics certification exam will be held in Boston on October 3 at the Predictive Analytics World event. This is the only Boston-area exam scheduled in 2013.  

Date: Monday, March 4, 2013
Speaker: Peter DeWan, PhD, Chief Scientific Officer and VP Analytics
Location: Bentley University, Center for Marketing Technology (CMT)
Title: Making a Business of Social Network
Analytics Abstract: At Activate Networks we have found two major areas for providing value using social network analytics. The first is to provide businesses with the methods for promoting ideas and behaviors into an existing network, including tasks such as finding influential nodes and prioritizing promotional efforts. The second is providing organizations with an understanding of how their internal networks function and how these stsructures affect important outcomes such as collaboration, innovation, or efficiency. This leads to recommendations for "rewiring" the network towards improvement. Using an example from each area, the talk will explain the problem and the ANI solution. This will lead to a discussion of the three current areas of focus for ANI and the plans for expansion and elaboration.  

Date: Monday, February 25, 2013
Speaker: Albert-Laszlo Barabasi
Location: The Center for Complex Network Research (CCNR) and Barabasi Lab
Title: Complex Networks: From the structure of the WWW to cellular organization
Abstract: Systems as diverse as the world wide web, Internet or the cell are described by highly interconnected networks with amazingly complex topology. These networks are the result of self-organizing processes governed by simple but generic laws, resulting in architectural features that makess various real networks much more similar to each other than one would expect by chance. I will discuss the order characterizing our interconnected world and its implications from network robustness to network control.

Date: Monday, January 14, 2013
Speaker: Dr. Les Servi, The MITRE Corporation
Location: Fidelity Investments @ 245 Summer Street
Title: A Mathematical Approach to Identifying and Forecasting Shifts in the Mood of Social Media Users
Abstract: Social media offers a promising opportunity to identify and understand the moods of people using these platforms, just as conventional radars help one idesntify and understand physical motion. To date, many of the methods used to analyze social media in this way are qualitative, relying on the inputs of human subject matter experts. Those quantitative approaches which have been validated are in their infancy. This paper presents a new quantitative approach to characterizing the mood of social media users that can complement existing qualitative methods. This novel method combines a validated computer program (LIWC) with a mathematical algorithm to follow trends in past and present moods and detect breakpoints where those trends changed abruptly. First steps have also been taken to further develop this method so that it can also predict future trends in moods and possibly forecast related events. Validation is an important aspect of this part of the overall study. Finally, preliminary guidance for putting the output of the breakpoint analysis and forecasting into context is provided. The paper concludes with an overview of directions for continued research.

Date: Monday, December 10, 2012
Speaker: Eric Kolaczyk, Boston University
Location: Boston University
Title: Statistical Analysis of Network Data
Abstract: Over the past decade, the study of so-called "complex networks" - that is, network-based representations of complex systems - has taken the sciences by storm. Researchers from biology to physics, from economics to mathematics, and from computer science to sociology, are more and more involved with the collection, modeling and analysis of network-indexed data. With this enthusiastic embrace of networks across the disciplines comes a multitude of statistical challenges of all sorts - many of them decidedly non-trivial. In this talk, we will cover a brief overview of some of the foundations common to the statistical analysis of network data across the disciplines, from a statistical perspective, in the context of topics like network summary and visualization, network sampling, network modeling and inference, and network processes. Concepts will be illustrated drawing on examples from bioinformatics, computer network traffic analysis, neuroscience, and social networks.

Date: Tuesday, March 6, 2012
Speaker: Rama Ramakrishnan, Ph.D.
Location: Verizon Laboratories
Title: Big Data meets Big Math: Customer Modeling in the Retail Industry
Abstract: Retailing is the quintessential B2C (business-to-consumer) industry. As such, one might expect retailers to be at the forefront of applying consumer-level modeling and optimization to key business decisions. This is not the case. For the most part, retailers continue to run their businesses with product and store level data and analytics. Recently, however, this has started to change due to two factors: The growing might of Amazon and its reputation as a very smart wielder of sophisticated customer analytics technology The fear that if their competitors exploit Big Data (from site logs, customer reviews and social media) before they do, they will be left behind As a result, retailers are paying more attention to analytic technologies that could help them tame Big Data, understand their millions of customers at a very granular level and translate this understanding into better decisions. In this talk, we share sdetails and early results from building and deploying customer-level models for highly individualized marketing at a retailer with over 50 million customers. We describe the modern, highly scalable cloud-based technologies that these models run on and the neat things that happen when numeric data and textual data are modeled together.  

Date: Wednesday, January 11, 2012
Speaker: Vladimir Shnaydman, Ph.D.
Location: Verizon Laboratories
Title: Strategic R&D project portfolio planning:- approaches, techniques, tools
Abstract: Portfolio planning is critical for developing long-term company strategy. The goal is to select "right" portfolio of internal and external R&D projects for funding, align company strategy and limited resources, optimize resource utilization, and manage portfolio risk to buffer the organization against unfavorable events. Such factors as insufficient/uncertain data and each company's unique business environment could contribute to the complexity of portfolio planning. It is also hard to validate modeling results due to a long planning horizon, and highly dynamic nature of business. Importance of portfolio planning and its complexity dictates application of advanced techniques based on OR methodology. OR portfolio planning models are much more efficient than multiple "simplistic" and sometimes inaccurate techniques. The presentation will include: Overview of tools for portfolio planning, their advantages and disadvantages Portfolio planning technique overview based on combined usage of optimization and simulation models to optimize portfolio and balance it across value, strategic goals, resources and risk. Optimization model (MIP) is used for portfolio selection, and simulation model - for portfolio risk assessment and analysis of risk mitigation strategies. Portfolio simulator also includes animation of portfolio workflow. Case studies and tools illustrating presented approach are related to portfolio planning for biopharmaceutical companies  

Date: Tuesday, December 13, 2011
Speaker: James C. Benneyan, PhD.
Location: Northeastern University
Title: Healthcare Systems Engineering: Past, Present, Future
Abstract: Problems with our healthcare system are well-known and staggering, including poor access, inefficient processes, equity disparities, practice variability, and patient safety issues, all at enormous costs. The enormity of this crisis has prompted the National Academy of Engineering, Institute of Medicine, and numerous others to advocate greater application of systems engineering and operations research over a decade ago, yet not much has changed. Management science, by whatever name, in fact has a long healthcare history, recently enjoying its fourth renaissance within academia. This talk is divided roughly into thirds - discussing the history of healthcare IEOR, examples of current applications, and important future directions if our field is to have more profound impact.  

Date: Tuesday, October 25, 2011
Speaker: Steve Sashihara, PhD.
Location: Bentley University Center for Marketing Technology
Title: 5 Steps to a Successful Optimization Project
Abstract: Optimization is a "breakaway" strategic capability that demands both technical excellence and business intelligence. To achieve success that can be measured from the boardroom to the operation's floor--and to avoid pitfalls that plague many projects--optimization must be designed and implemented by the right team with the right vision and capabilities. Author Steve Sashihara will discuss best practices from opportunity identification through implementation and scale-up, using real-life examples at companies such as Intel, McDonald's and UPS, which have used optimization to drive up value, re-allocate resources, streamline processes and optimize their assets. The discussion is based on Steve's new book, The Optimization Edge , (McGraw-Hill, 2011) the first step-by-step guide to optimization for the business executive.  

Date: Tuesday, March 1, 2011
Speaker: Steve Gallant
Location: Emptoris Inc.
Title: Incremental Response Modeling: Uses, Algorithms and Comparisons
Abstract: A major task for marketing departments is to decide which names should receive a promotion. For example, a retailer may wish to send 20% off coupons to customers to encourage them to shop. However it would be too costly to send the coupons to every customer, even just considering postage and production costs. For this reason, marketers routinely use predictive modeling to find appropriate subsets for promotions. Typically they will generate some sort of statistical model based upon who responded to the previous promotion, when directed at a random sample of that list. So in the 20% off case, who should receive coupons? At first, a traditional response model will appear good in this situation, because it successfully predicts those who will shop. Unfortunately, many of these people would have shopped even without the coupon, so the net effect of sending them a coupon is to reduce margin. Incremental Response Modeling (IRM) seeks to predict those who will shop only if they receive a coupon. This talk will introduce Incremental Response Modeling, and present several algorithms for building IRM predictive models. We will also look at initial results in an ongoing comparison of methods using actual customer data from retail and financial domains.  

Date: Tuesday, January 25, 2011
Speaker: Anwiti Bahuguna
Location: Center for Marketing Technology at Bentley University
Title: Asset Management Research
Abstract: The heavy losses suffered by many investors during the financial crisis have caused some to question the efficacy of diversification. During the financial crisis and the ensuing recession, the classic "diversifying" asset classes, such as U.S. small cap stocks and emerging market equities, not only failed to moderate portfolio losses, in some cases they exacerbated them. This talk is a summary of our findings and a discussion of our philosophy for managing multi-asset class portfolios. In our opinion "Diversification is NOT dead". However, the cost of risk management benefits provided by genuine diversification has increased. Strategic portfolio allocation, i.e. deciding how to allocate between stocks, bonds and other asset classes, for the long run, can be done in many ways. Some conventional methods, using standard optimization techniques and some of the more recent findings will be discussed.  

Date: Tuesday, November 23, 2010
Speaker: Professor Anna Nagurney
Location: Emptoris Inc.
Title: Supply Chain Networks: Challenges and Opportunities from Analysis to Design
Abstract: Supply chain networks provide the backbones for our economies since they involve the production, storage, and distribution of products as varied as vaccines and medicines, food, high tech products, automobiles, and even energy. Many of the supply chains today are global in nature and present challenging aspects for modeling and analysis. In this talk I will discuss different perspectives for supply chain modeling, analysis, and computation based on centralized vs. decentralized decision-making behavior, along with suitable methodological frameworks. I will also highlight applications of our research to empirical electric power supply chains, to mergers and acquisitions, and even to humanitarian logistics. Such timely issues as risk management, demand uncertainty, outsourcing, and disruption management in the context of our recent research on supply chain network design and redesign will also be discussed. Suggestions for new directions and opportunities in healthcare and sustainable supply chain networks will conclude this talk.  

Date: Tuesday, November 2, 2010
Speaker: Greta Ljung
Location: Northeastern University
Title: Solving Estimating Potential Losses from Natural Catastrophes
Abstract: Natural hazards such as earthquakes, hurricanes, tornadoes, winter storms, and wildfires cause high economic losses and loss of life, both in the United States and elsewhere. The occurrence of these events is of concern to government agencies, emergency planners, insurers, and other stakeholders. The development of effective risk management strategies requires a good understanding of potential losses from each hazard. The estimation of potential losses is challenging due to the relatively low frequency of some of the costliest events, such as strong earthquakes or major hurricanes. Use of historical losses is often insufficient for loss estimation because of inflation, population growth in risk-prone areas, and the increases in building stock and property values that may have occurred since the last major event happened. Catastrophe modeling, also known as cat modeling, provides a useful tool for evaluating the potential losses associated with natural hazards. These models, which rely on computer simulations of catastrophic events, were first introduced in the 1980s and are today widely used by insurers and others to assess potential risk. This presentation will describe the general structure of catastrophe models, followed by a detailed discussion of models used to evaluate the financial impact of hurricane landfalls along the U.S. coastline. The primary focus will be on the hazard component of the model, which uses statistical methods and probability tools to evaluate the frequency and intensity of landfalling hurricanes for the entire coastline and for different sub-regions along the coast. The uncertainties associated with the resulting loss estimates will also be discussed.  

Date: Wednesday, October 13, 2010
Speaker: Horia Tipi
Location: Center for Marketing Technology (CMT) at Bentley College
Title: Solving extremely large scale optimization problems using FICO's Xpress Optimization Suite
Abstract: Even vast improvements in optimization solver engine speed have not been sufficient to deal with the challenge of massive problems. Many optimization problems are too large to fit into memory or too hard to solve at all, or, for many applications, too hard to solve within the required time. This is when decomposition -- breaking the problem into subproblems and solving them either sequentially or in parallel -- is the solution. We will present: - Decomposition techniques from a practical perspective - How the FICO Xpress Optimization Suite provides two approaches for decomposition - How multi-problem and multi-model approaches work within the Xpress-Mosel modeling language - How FICO clients have addressed "super-size" problems using Xpress

Date: Tuesday, September 28, 2010
Speaker: Victor Lo
Location: Buckingham Browne & Nichols School
Title: Causal Business Analytics [Joint Meeting with BCASA]
Abstract: Statistics, Data Mining, and Operations Research have been widely applied in many business areas over the past several decades. Many telecommunication, credit card, and retail corporations, for examples, routinely make use of customer data to understand customer needs and predict future behavior, resulting in highly targeted actions to improve customer relationships and maximize profitability. Actions of business firms may include sales interactions, direct mails, site optimization, product recommendation, pricing change, incentive offering, or simply broadcast advertising. How do we know if a business action is successful in achieving its objective? Can we carry out scientific experiments in a business setting? How can we use advanced analytics to optimize business goals? This lecture will examine how to address the causal impact of business actions. The analytics process includes design, measurement, predictive modeling, and optimization. Illustrations from marketing analytics will be given. Methodologies employed include A/B testing, fractional factorial design, propensity scoring, statistical modeling, cross-sectional time series analysis, machine learning, and integer programming. Future research opportunities will also be given.  

Date: Wednesday, September 15, 2010
Speaker: Professor Nathan Eagle ( MIT )
Location: The MITRE Corporation Title: Inferring Social Network Structure using Mobile Phone Data
Abstract: Petabytes of data about human movements, transactions, and communication patterns are continuously being generated by everyday technologies such as mobile phones and credit cards. This unprecedented volume of information facilitates a novel set of research questions applicable to a wide range of development issues. In collaboration with the mobile phone, internet, and credit card industries, my colleagues and I are aggregating and analyzing behavioral data from over 250 million people from North and South America, Europe, Asia and Africa. I will discuss a selection of projects arising from these collaborations that involve inferring behavioral dynamics on a broad spectrum of scales; from risky behavior in a group of MIT freshman to population-level behavioral signatures, including cholera outbreaks in Rwanda and wealth in the UK. Access to the movement patterns of the majority of mobile phones in East Africa also facilitates realistic models of disease transmission as well as slum formations. This vast volume of data requires new analytical tools - we are developing a range of large-scale network analysis and machine learning algorithms that we hope will provide deeper insight into human behavior. However, ultimately our goal is to determine how we can use these insights to actively improve the lives of the billions of people who generate this data and the societies in which they live.  

Date: Wednesday, November 18, 2009
Speaker: Professor David Simchi-Levi ( MIT )
Location: Verizon Network & Technology Laboratory
Title: Creating Value in a Volatile World
Abstract: With the economic recession in full swing, supply chain managers are facing a growing array of risks. Fluctuating transportation costs, high volatility in demand volume and mix, commodity price volatility, increase in labor costs in developing countries and the pressure to reduce inventories are just a few of the challenges that companies are struggling to overcome today and will likely face in the future. In such an environment it is important to focus on three dimensions: Cost, Cash and Service. That is, it is important to identify strategies to reduce cost and cut working capital (cash) while at the same time maintain or increase service levels. Of course, the increase in volatility and risks demand strategies that, while reducing cost and working capital, allow the firm to better respond to changes in demand volume and mix, exchange rates, technology or labor costs. In particular, it is important to implement a strategy that allows the firm to cut costs while at the same time prepare for growth. This is the focus of our talk.  

Date: Tuesday July 14, 2009
Speaker: Professor Andrew Lo (MIT Sloan School)
Location: The MITRE Corporation (Bedford, MA & McLean, VA)
Title: "Kill All the Quants"?: Models vs. Mania in the Current Financial Crisis
Abstract: As the shockwaves of the financial crisis of 2008 propagate throughout the global economy, the "blame game" has begun in earnest, with some fingers pointing to the complexity of certain financial securities, and the mathematical models used to manage them. In this talk, I will review the evidence for and against this view, and argue that a broader perspective will show a much different picture. Blaming quantitative analysis for the financial crisis is akin to blaming F = MA for a fallen mountain climber's death. A more productive line of inquiry is to look deeper into the underlying causes of financial crisis, which ultimately leads to the conclusion that bubbles, crashes, and market dislocation are unavoidable consequences of hardwired human behavior coupled with free enterprise and modern capitalism. However, even though crises cannot be legislated away, there are many ways to reduce their disruptive effects, and I will conclude with a set of proposals for regulatory reform.  

Date: Wednesday, April 22, 2009
Speaker: Professor Venkatesh Saligrama, Boston University
Location: Verizon Laboratories (Waltham, MA)
Title: Video Analytics over Camera Networks
Abstract: Network of video cameras, developed in the last decade or so, permit today pervasive, wide-area visual surveillance. The main difficulty is that video data by its nature produces a high degree of clutter and it is difficult to identify the truly relevant information from clutter particularly in urban environments. Conventionally, this problem has been handled by an object-based approach wherein an object may first be tagged, identified, classified, and tracked before behavior modeling and abnormal detection. This paradigm is neither scalable to complex urban environments or to networks of video cameras having limited communication capability. We explore a location-based approach for behavior modeling and abnormality detection. We proceed directly with event characterization and behavior modeling at the pixel(s) level based on motion labels obtained from background subtraction. Our method requires little processing power and memory, is robust to motion segmentation errors, and general enough to monitor humans, cars or any other moving objects in uncluttered as well as highly-cluttered scenes.  

Date: Wednesday, February 25, 2009
Speaker: Prof. Dominique Haughton
Location: Emptoris, Inc. (Burlington, MA)
Title: Multilevel models and living standards in Vietnam
Abstract: This talk describes an investigation of living standards in Vietnam from the point of view of a study of real household per capita expenditure by means of two multilevel models. Policy implications of this work for poverty targeting will be discussed as we go along. *First we will give an introduction to the Vietnam Household Living Standards Surveys (VHLSSs). *We will then demonstrate how the use the software MLWin to construct a multilevel model with the logarithm of real per capita expenditure as a dependent variable, and a number of household characteristics such as age and education of the head of household, etc. and an urban/rural location indicator as independent variables. The model includes four nested levels, the household (level 1) inside a commune (level 2) inside a district (level 3) inside a province (level 4). *We will discuss how the model yields random effects in the intercept that provide an estimate of differences in living standards due to geographical location, when household characteristics are controlled for. We will also suggest that random effects identified in the independent variable urban/rural can be seen as location-specific random contributions to the urban/rural gap above and beyond the effects of known location characteristics, such as level of education of the population, etc. *We then demonstrate how the multilevel model can be used to obtain small area estimates of the mean (logarithm of) household per capita expenditure at the commune level. *Further current perspectives will then be discussed, regarding an extension of our model to accommodate data from three Vietnam Household Living Standards Surveys, of 2002, 2004 and 2006.  

Date: Wednesday, October 29, 2008
Speaker: Prof. Karl Rexer
Location: Emptoris, Inc. (Burlington, MA)
Title: Data Miners' Views on Data Mining: Survey Findings & One Consultant's Perspective
Abstract: Results of the 2nd Annual Rexer Analytics Data Miner Survey will be presented. The survey of 348 data miners examined the algorithms and tools currently being employed, priorities considered in selecting these tools, the types of data analyzed, challenges encountered, and solutions provided. Trends between the 2007 and 2008 findings will be highlighted. Additionally, Karl will discuss his perspectives on data mining software and algorithms, and will provide tips for achieving success in data mining projects.  

Date: Wednesday, October 1st, 2008
Speaker: Prof. DIMITRIS BERTSIMAS
Location: Verizon Network and Technology (Waltham, MA)
Title: OR in health care: opportunities, perspectives and progress
Abstract: In recent years the availability of massive amounts of electronically available data involving millions of people and the development of new data mining algorithms present an exciting new opportunity for Operations Research to have a significant impact in health care. We discuss our research efforts in assessing the risk of patients, their quality of care and also propose a new data based assessment for cancer research. We further discuss further research directions.  

Date: Tuesday, June 10th, 2008
Speaker: Prof. Alfred Blumstein
Location: Emptoris, Inc. (Burlington, MA)
Title: Bringing OR Perspectives to the Criminal Justice System
Abstract: OR practitioners are likely to find the CJS one of the most primitive of social systems. Over the past forty years, I and a number of colleagues have been involved in bringing OR techniques of quantitative modeling, system perspective, and planning to that system The issues addressed have included modeling of criminal careers as a stochastic process, bringing those analyses to the assessment of incapacitation effects of incarceration, review of trends in incarceration and factors contributing to those trends. We specifically focus on the interaction of incarceration and drug markets and identify some of the unintended counterproductive effects of that response to the drug problem. Note that the slides and an audio recording of the talk are available for Boston Informs chapter members. Please contact the webmaster for details on how to retrieve the files.  

Date: Wednesday, April 30th, 2008
Speaker: Prof. Arnold Barnett
Location: Emptoris, Inc. (Burlington, MA)
Title: The Electoral College: Its Care and Cure
Abstract: As the 2000 election so vividly showed, it is Electoral College standings rather than national popular votes that determine who becomes President. But how do we understand what is happening under the Electoral College rules? When a poll reports that (say) Clinton would have 45% of the votes in a Clinton-McCain contest and McCain 43%, which one is ahead in the Electoral College? And what is the probability that this candidate is genuinely ahead, taking into account the statistical sampling error that attends each statewide result? Some people think that the Electoral College should be replaced by a national popular vote. However, that will not happen. We will discuss a modification of current procedures that would come very close to a national popular vote, yet actually increase the role of the smaller states that benefit from present arrangements. Conceivably, the system could be in place by 2012. Not that one should bet on it.  

Date: Wednesday, November 28, 2007
Speaker: Prof. David Jensen
Location: Verizon Laboratories (Waltham, MA)
Title: Learning and exploiting statistical dependencies in networks
Abstract: Networks are a ubiquitous representation for natural, technological, and social systems. We live embedded in social and professional networks, we communicate through telecommunications and computer networks, and we represent information in documents connected by hyperlinks and bibliographic citations. Only recently, however, have researchers developed techniques to analyze and model data probabilistic dependencies in these networks. These techniques build on work in artificial intelligence, statistics, databases, graph theory, and social network analysis, and they are profoundly expanding the phenomena that we can understand and predict. However, new frontiers await.   In this talk, I will survey some recent work in learning probabilistic models of relational data, and discuss several applications of these techniques, including fraud detection in the U.S. securities industry. I will argue that current techniques are capable of learning only a subset of the knowledge needed by practitioners in these domains, and that further work in analyzing networks offers a unique ability to produce the full range of knowledge needed in a wide range of applications, including a unification of work in machine learning, causal inference, and agent-based simulation.  

Date: Thursday, October 11, 2007
Speaker: Prof. Karla Hoffman
Location: Riverfront Conference Center (Cambridge, MA)
Title: The Dance Of The Thirty-Ton Trucks: Dispatching And Scheduling In A Dynamic Environment
Abstract: We report on the application of operations research to a very complex scheduling and dispatching problem. Scheduling and Dispatching is never easy, but the scheduling of concrete deliveries is particularly difficult for several reasons: 1) concrete is an extremely perishable product – it can solidify in the truck if offloading is delayed by a few hours; 2) customer orders are extremely unpredictable and volatile – orders are often canceled or drastically changed at the last minute; 3) the concrete company overbooks by as much as 20% to compensate for customer unpredictability; 4) many orders require synchronized deliveries by multiple trucks; 5) when a truck arrives at a customer site, the customer may not be ready for the delivery or a storm may negate the ability to use the concrete; and 6) most of the travel takes place in highly congested urban areas making travel times highly variable. In order to assist the dispatchers, schedulers, and order-takers at this company, we designed and implemented a decision support tool consisting of both planning and execution tools. The modules determine whether new orders should be accepted, when drivers should arrive for work, the real-time assignment of drivers to delivery loads, the dispatching of these drivers to customers and back to plants, and the scheduling of the truck loadings at the plants. For the real-time dispatching and order-taking decisions, optimization models are solved to within 1% of optimality every 5 minutes throughout the day. This nearly continuous re-optimization of the entire system allows quick reactions to changes. The modeling foundation is a time-space network with integer side constraints. We describe each of the models and explain how we handle imperfect data. We also detail how we overcome a variety of implementation issues. The success of this project can be measured, most importantly, by the fact that the tool is being ported by the parent company, Florida Rock, to each of its other ready-mix concrete companies. Secondly, the corporation is sufficiently convinced of its importance that they have begun promoting this methodology as a "best practice" at "World of Concrete" and "ConAgg" industry conventions.  

Date: Tuesday, Sept, 18, 2007
Speaker: Prof. Cynthia Barnhart
Location: Emptoris, Inc. (Burlington, MA)
Title: Airline Optimization: If we are so good at it, why are things so bad?
Abstract: Airlines have a history of OR work and have spent a lot of money optimizing their schedules. So why do we keep hearing about all the problems at the airports? There is still some work to do. This talk covers some problem areas, and some proposed solutions.  

Date: Wednesday, June 13, 2007
Speaker: Prof. Yossi Sheffi
Location: Verizon Laboratories (Waltham, MA)
Title: The Resilient Enterprise
Abstract: What happens to a company when the unimaginable occurs? When an earthquake hits its primary contract manufacturer? When labor strikes shut down an entire port? When terrorists cripple a transportation system? In this talk, Yossi Sheffi, Professor of Engineering at MIT and Director of the MIT Center for Transportation and Logistics, describes how a company’s survival and prosperity depend more on what it does before such a disruption occurs than on the actions it takes as the event unfolds. The talk is based on his award-winning best seller "The Resilient Enterprise: Overcoming Vulnerability for Competitive Advantage" (see http://resilient-enterprisemit.edu/) which was reviewed by dozens of publications, including the WSJ, NYT, and The Economist. The FT called in one of the best business books of 2005. The talk explores high-impact/ low-probability disruptions, focusing not only on security but on corporate resilience¬the ability to bounce back from such disruptions¬and how resilience investments can be turned into competitive advantage. It demonstrates the concepts with dozens case studies and examples.  

Date: Tuesday May 8, 2007
Speaker: Thomas Leighton
Location: Akamai Cambridge (Cambridge, MA)
Title: The Akamai Story: From Theory to Practice
Abstract: Akamai Technologies is the leading global service provider for accelerating content and business processes online. Prof. Leighton will describe Akamai's origins and business. The talk will be followed by a tour of Akamai's Network Operation & Control Center (NOCC).  

Date: Tuesday March 20, 2007
Speaker: Dr. John S. Hammond, co-author of Smart Choices, A Practical Guide to Making Better Decisions
Location: Verizon Laboratories
Title: The Hidden Traps in OR/MS
Abstract: As OR/MS professionals our models often require subjective numerical inputs and subjective adjustment of outputs in the course of the user making decisions. How good are these judgments? It turns out that they are subject to ingrained psychological biases that can sabotage the decisions, sometimes destroying much of the benefit of an otherwise fine model. Most decision makers and indeed many OR/MS professionals are blissfully unaware of these traps, in spite of the fact that Daniel Kahneman won the 2002 Nobel Prize in Economics for his ground-breaking work on them, work reflected in this talk. Our speaker, John Hammond, will introduce us to some of the most important traps, illustrate where they occur, and suggest ways to reduce their impact. The session, based in part on his best-of-HBR Harvard Business Review article, “The Hidden Traps in Decision Making,” will be highly interactive.  

Date: Thursday, October 26th, 2006
Speaker: Dr. Daniel Bienstock, Professor of Operations Research at Columbia University
Location: Emptoris, Inc.
Title: Catastrophic blackouts: problems, models, solution methods
Abstract: The August, 2003 blackout that affected the Northeast of the US and Canada, and similar events in other countries, have brought attention on the fact that national power transmission networks have become, over the past few decades, large, complex, and exposed to catastrophic failures. From an OR perspective, the problem is complicated for two reasons: first, power networks follow complex laws of physics that are not easy to model, and second, blackouts are initiated by combinations of exogenous events that are extremely unlikely even as they prove damaging. In this talk we will describe ongoing work to tackle this problem.  

Date: Tuesday, Sept. 26, 2006
Speaker: Dr. Tom Magnanti, Dean of the School of Engineering at MIT and former President of INFORMS
Location: Verizon Laboratories
Title: When OR is AND: Perspectives on Theory and Practice in Operations Research
Abstract: When is it possible (desirable) to bring together theory AND practice, to have both rigor AND relevance? Unlike some fields that place emphasis on one extreme or the other, Operations Research has historically been motivated in large part by both. This talk will reflect on the interplay between theory and practice – OR is AND when OR is Operations Research. It will focus on applications of operations research including several in engineering that might not be familiar to an operations research audience.  

Date: Thursday, Aug 3, 2006
Location: MIT Lincoln Laboratories
Speaker: Colonel Darrall Henderson
Title: Operations Research and West Point Supporting a Nation at War
Abstract: This talk will share insights about the speaker's tour in the Multinational Force - Iraq Headquarters. Specifically, he will discuss analysis supporting the four lines of operation in the Campaign Plan for OIF (Security, Governance, Economic, and Information). The pace of planning and combat operations in Iraq requires one to quickly collect, interpret and assimilate data and information to aid combatant commanders. In order to accommodate these unique requirements, an eclectic mix of operators, strategists, planners, analysts, and civilian subject matter experts reminiscent of the early days of Operations Research is required. Additionally, the speaker will discuss ongoing efforts at the United States Military Academy at West Point, NY to provide analysis to support a Nation at War.  

Date: Tuesday, June 6, 2006
Location: Verizon Laboratories
Speaker: Dr. Mitch Burman
Title: Engineering Increases HP Productivity by $780M
Abstract: As HP installed a system for manufacturing ink-jet printers, it discovered that it was only going to perform at 20% of anticipated output levels. After several unsuccessful attempts to use standard software tools, we determined the need to use a first principles industrial engineering approach. As a result, we developed an analytical model of the production line dynamics that allowed HP to achieve the desired results. The experience demonstrated that there was no substitute for a rigorous engineering approach. This talk will focus on the HP case study, but also touch upon the pitfalls of relying too much on software to solve industrial operations challenges.    

Date: Wednesday, May 3, 2006
Location: Emptoris, Inc.
Speaker: Dr. Nitin Patel
Title: Introduction to Data Mining
Abstract: This talk will introduce the rapidly evolving, multidisciplinary field of data mining. Data mining is rooted in the fields of statistics and artificial intelligence and has been gaining momentum in managerial applications in areas such as customer relationship management, finance, e-business, and operations. Data mining seeks to exploit the large volumes of transactional data that are routinely stored in databases to record operational steps such as moving, storing, testing, and selling products or delivering services like financial credit, maintenance and call center support. As is often the case with emerging fields having substantial commercial potential, there is considerable hype concerning data mining. My aim is to enable a balanced view of data mining for management scientists interested in harnessing this technology to improve business decisions. I will provide an overview of the types of problems addressed by data mining and the key ideas that underlie its approach. I will use the method of k-nearest neighbors to illustrate the data mining philosophy of ‘let the data do the talking’.  

Date: Wednesday, March 8, 2006
Location: Verizon Laboratories
Speaker: Dr. Rama Ramakrishnan
Title: Math and the Merchant: The Application of Econometrics, Machine Learning and Optimization Technologies to Retail Decision-Making
Abstract: Retailing is a global, multi-trillion dollar industry and touches just about every person on the planet. Yet, despite its size and complexity, most retail decisions are made primarily on instinct. This has started to change in the last decade with the availability of granular and timely sales data coupled with the development of sophisticated decision-support software that analyzes this data and recommends optimal decisions. Retailers are rapidly adopting this technology to help improve the financial consequences of the numerous decisions they make every day. In this talk, we focus on decisions made by retailers in the merchandising process, perhaps the most important business process within retail. We identify some of the core analytical decision problems in this area and describe the algorithmic/modeling techniques that have been developed to address these problems. We highlight the inter-disciplinary nature of “winning” approaches i.e., they tend to be hybrids that draw on ideas from disciplines such as econometrics, machine learning and optimization. We conclude with a summary of the financial impact of these techniques on retailers’ financials (and stock prices!) worldwide.  

Date: Thursday, January 26, 2006
Location: Optiant
Speaker: John Neale
Title: Supply Chain Inventory Optimization: A Market Description and Case Study
Abstract: This talk will consist of two parts. The first part will provide an overview of the supply chain Inventory Optimization (IO) software market. I will describe the different problems that constitute the space, the evolution of the market and the different companies that offer IO solutions, and the operations research challenges of working in the space. The second part of the talk will present a case study of a successful IO project at Elmer’s Products. I will describe Elmer’s situation and supply chain, the approach taken, the challenges faced (both technical and organizational), and the results achieved.  

Date: Wednesday, December 7, 2005
Location: Emptoris
Speaker: Dick Larson
Title: The OR Profession: Past, Present, Future Prospects and Perils to Avoid
Abstract: In this talk we discuss STATE OF THE PROFESSION. How INFORMS is emphasizing this aspect of Operations Research (OR), using observation, data and analysis to solve real and important problems. We provide examples of current 'hot topics' in OR research from many of the different segments of the profession. MARKETING THE PROFESSION. Efforts by INFORMS to tell others about the OR profession, now called "The Science of Better," including OR's implemented accomplishments and its importance in efficiently managing organizations. ARE WE BECOMING TOO NARROW? We will then discuss a new emerging field in the US and Europe that increasingly looks like Phil Morse's OR, while many in our profession are becoming increasingly narrow, increasingly mathematical.  

Date: Wednesday, Oct 19, 2005
Location: Verizon Laboratories
Speaker: Dr. Irv Lustig, Manager of Technical Services, ILOG Direct
Title: Computational Progess in Optimization
Abstract: The past 15 years have seen an explosive growth in the number of applications of linear and integer programming. The evolution of powerful algorithms for solving these problems--together with ever more powerful computers--has brought the application of optimization to the desktop. Irv will describe the computational state-of-the-art in optimization and the key advances that have led to a tremendous increase in solving power. The result of this increased power is that many problems once considered unsolvable are now solvable, often in a matter of minutes.