-
Analytics 2
The objective of Analytics 2 is to provide you with a strong background in predictive analytics. We will emphasize learning how to be an intelligent "consumer" of analytics. This, in turn, will help you make effective decisions as a manager using predictive analytics. We will use sophisticated statistical and predictive analytics methods to understand and anticipate the effects of our actions. These methods include confidence intervals, hypothesis testing, A/B testing, multiple regression, and supervised and unsupervised machine learning models such as neural networks and cluster analysis. We will apply these methods to problems from all organizational functions including management & strategy, operations, economics, marketing, finance & accounting, and to a variety of industries. In addition, you will become skilled in performing various analyses via hands-on experience using the R statistical programming language.
-
Fundamentals of Web Programming
This hands-on minicourse will teach the basics of web programming (Javascript, HTML, and CSS). During the course, you will build a web-based e-commerce site from scratch. By the end of the course you will be able to reason effectively about designs for and potential capabilities of web applications. There are no prerequisites for the course.
-
Tools for Improving Operations
This course introduces frameworks and tools designed to enhance operational performance. Our view of operations is very broad in that we explore how firms execute in a variety of contexts (hospitals, quick service restaurants, retailers, hotels, professional service organizations, and more). Our main focus will be to identify simple, powerful approaches to improving operations.
In addition to learning how to identify and execute improvement opportunities, our objectives include:
• Equipping future general managers, consultants, and operations managers with the perspectives and skills needed to effectively use operations as a competitive weapon.
• Exploring new operating models that allow for the optimal use of resources – including the building of sustainable capabilities (e.g. circularity).
• Discovering the power of experimentation and innovation tournaments to identify and measure operational improvement opportunities.
-
AI-Driven Analytics and Society
The last decade has brought us tremendous advances in the power and sophistication of data- driven decision-making techniques at our disposal. Encouraged by this progress, we are witnessing a broad deployment of these techniques across the world. They now touch on and sometimes even govern just about every aspect of how businesses, and even people, operate on a day-to-day basis.
However, as much as these techniques were deployed with the promise of bringing a decisively positive change, it has become abundantly clear that they often are a mixed blessing, at best. Indeed, it turns out that the interface of algorithmic decision-making and society is rife with subtle and non-obvious interactions, undesirable feedback loops, and unintended consequences. How should we make sense of and navigate these issues?
The goal of this seminar is to survey some of the key challenges emerging in the context of the societal impact of data-driven decision making, as well as to create a forum where the students can discuss potential approaches to addressing these challenges. We will aim to discuss questions such as: How should businesses responsibility use, interpret, and make decisions from the output of machine learning models? How can we ensure big data sets are unbiased, fairly labeled, and being used responsibly by companies? What challenges will we face as businesses shift toward using generative AI and large language models for operations such as online customer service? Why does fake news spread faster than truthful news on online platforms like social media, and how do we combat it? Will automation replace unskilled labor, or simply make workers more productive?
Intense student involvement in both the presentation and the class discussion of the scientific papers is required. Like all RTP seminars, there will be a focus on using academic research to help you learn the analytical rigor to be an effective manager in an increasingly complex world.
This course meets the Ethics and Social Responsibility (ESR) requirement.
-
Data Mining for Business Analytics
Data mining is a group of analytics methods that primarily deal with prediction and classification. This course will cover the following topics: data cleaning, exploration and visualization, logistic regression, classification and prediction trees, naive Bayes estimation, and ensemble methods. These methods are applicable in many industries. Datasets used for class assignments come from industries such as healthcare, transportation, finance, and criminal justice.
This course builds on the core Analytics 1 & 2 courses. Class time will generally include 1) discussion of the homework, 2) presentation and discussion of new material, 3) “lab time” where students will be working individually or in small groups on assignments, and 4) discussing the lab assignment.
-
Data-Driven Analytics for Innovative Operating Models
We are now witnessing the growing significance of data analytics and artificial intelligence (AI) in our society. They have found uses in both business and public domains spanning from forecasting consumer demand to mitigating supply chain disruptions to developing evidence-based public health policies. Whether you will work in a traditional enterprise or a technology-driven startup, it is essential to acquire the necessary concepts and tools to navigate today’s data-rich environment.
This minicourse is designed to introduce students to a broad range of contexts where data analytics and AI transform how business is conducted and how decisions are made, ultimately fostering innovative operating models. The course will give students an opportunity to apply the concepts and tools they have learned from the Analytics core courses to real-world data and decision problems. While covering various industries, the course focuses on emerging startups and technology companies. The final project of the course requires student teams to develop a data-driven innovative operating model. The anticipated mix for the course is roughly 50% quantitative and 50% qualitative. Familiarity with a statistical regression software (e.g., Excel with the Data Analysis Tools) is needed for the course.
-
Management of Service Operations
The service sector dominates the economies of most developed nations. Worldwide, services account for 64% of GDP and 40% of employment, and in the United States the service sector accounts for 76% of GDP and 85% of employment. In addition to the “pure” service sector, the delivery and support of many goods involves a significant service component. The challenges involved in managing services have been complicated by globalization, for many services are now delivered by service supply chains that involve multiple firms and cross national boundaries.
In this class we will engage with cases, exercises and concepts constructed to develop our collective ability to design, manage and improve service organizations. The class focuses on three broad topics: (i) the design of services (ii) managing variability, and (iii) innovation and growth of service businesses. This will be an immersive class grounded in practice. We will apply quantitative concepts discussed in Tuck’s Core Ops course to service businesses and explore managerial dilemmas faced by real companies operating in health care, financial services, hospitality, platforms among others.
-
Optimization Modeling for Prescriptive Analytics
This mini course expands on the core Analytics sequence through a deeper dive into the art of modeling, centered around essential tools in optimization. The goal of the course is to extend beyond predictive analytics and to develop richer prescriptive models for optimizing business operations in various marketplaces. We will focus on the modeling of prescriptive questions in a way that can be simply stated, solved efficiently, and whose insights can be communicated clearly.
Every class will be entirely “hands on” with an emphasis on active problem solving for more value-added learning. Each week will focus on a central topic in optimization, with the first session of each week centered around modeling techniques and the second session putting these skills into action with a data-driven case. Throughout the course we will focus on both classical management problems, such as production planning and commodity shipping, as well as modern operational problems, such as COVID-19 testing, cloud resource allocation, premium ride-hailing services, and personalized advertising through generative AI.
Topic wise, the course first provides an overview of the major types of linear programs, of the sort featured in the core, proceeding to more general models of strategic planning and control. Next, the course examines network models, including familiar problems such as optimal transportation routing (``special'' network models) as well as general network-flow models. Then, we cover the formulation and solution of optimization models with logical constraints. We conclude by tackling non-linear models and analyzing algorithms for heuristic solutions to optimization models.
-
VBA Programming
This minicourse teaches the fundamentals of computer programming using MS Excel's macro language, Visual Basic for Applications (VBA), as the language of instruction. The course starts by teaching students to simplify and extend code generated by Excel's macro recorder, and then builds on that base toward developing applications that analyze information and enhance decision making. Special attention will be given to mastering good programming style and building a solid base to continue learning.
-
Professional Decision Modeling
This minicourse extends core Analytics with a series of weekly case assignments using Excel and (to a limited extent) Tableau. The first case blends data analysis and spreadsheet modeling to examine global energy and development. The second case evaluates a Tuck alum’s investment, subsequent development, and recent sale of a small hydropower generation asset in Scotland. The third case builds a structured finance cash flow waterfall to generate insight into mortgage asset securitization risk. The fourth case uses Excel's PowerQuery to organize U.S. wine industry survey data with the aggregate results analyzed with pivot tables and pivot charts to create a comprehensive survey report. Students choose most weeks whether to work as individuals or in teams (but with intermediate, individual deliverables) to design and build spreadsheet models, analyze results, and advise management.
-
Supply Chain Management
A supply chain is comprised of all parties involved, directly or indirectly, in fulfilling a customer demand. The integrated management of this network is a critical determinant of success in today’s competitive environment. Companies like Amazon, Inditex, Intel, Johnson & Johnson, Lenovo, and Walmart are proof that excellence in supply chain management is a must for financial strength and industry leadership.
With increasing competition around the globe, supply chain management is both a challenge and an opportunity for companies. Hence a strong understanding of supply chain management concepts and the ability to recommend improvements should be in the toolbox of all managers. The objective of this course is to introduce you to the key concepts and techniques that will allow you to analyze, manage and improve supply chain processes for different industries and markets. At completion of this course, you will have the skills to assess supply chain performance and make recommendations to increase supply chain competitiveness.
The course covers a wide range of supply chain topics including supply chain network design, inventory management, strategic sourcing, supply chain contracting, and supply chain disruptions. Each topic will be discussed using a combination of models, case discussions, and readings. We will use a data-driven approach where tools and analysis start with realistic data.