15.572 - Analytics Lab: Action Learning Seminar on Analytics, Machine Learning and the Digital Economy
Instructors: Sinan Aral, Erik Brynjolfsson
In this seminar, student teams design and deliver a project based on the use of analytics, machine learning, large data sets, or other digital innovations to create or transform a business or other organization. The course is open by permission to MBAs, EMBAs, Sloan Fellows, and to students in other MIT programs with relevant coursework or experience in analytics, statistics, and information technology. A set of organizations, including sponsors of the MIT Initiative on the Digital Economy will offer projects for teams to work on, but students may also propose their own ideas and sites. The course culminates with presentations of final project results to an audience including experts, entrepreneurs and executives. Fall 2015, 9 units.
Class meeting: Tuesdays, 4-5:30pm in September and October, plus a matching workshop in September and a final presentation workshop in December (dates TBA).
Fall 2014 Syllabus
The application for Fall 2015 is available to MBAs, EMBAs, and other MIT graduate students starting on May 1. We will hold a separate application period for Sloan Fellows in July.
Selective admission (no bidding necessary): Relevant coursework or experience in analytics, statistics, and information technology; course open by instructor permission only; applications considered on the basis of relevant learning, experience, and motivation toward data analytic work, with extra weight given to data analytic courses taken and to data analytic project and job experience; attention given to a representation of students with technical and computational experience, managerial experience, experience implementing analytical models, and entrepreneurial work using analytics.
The course is not open to listeners and in-person attendance is mandatory.
For questions, please contact Susan Young <susany @ mit.edu>; also see slides presented at April 2015 Action Learning Open House.
Projects from 2014 included:
1. Prime Share of Wallet (Amazon)
- Find new ways to differentiate customers for increased sales
- Data: clean but overwhelming: 9 million observations on 170k anonymized customers across 75 product groups = 200 million points of data
- Team effort: feature engineering to create new, manageable variables; data visualization (R and STATA); validate differentiators
- “Finding the needle in the haystack you didn’t know you were looking for.”
2. Big Data as a Service (Amazon)
- Develop demand forecasting of value to Amazon’s retail vendors
- Data: 1 million records of daily transactions of one product group (textbooks), 16 variables, no vendor identification
- Team effort: Correlations, data visualization (Loess Regression with R), exploration of best sales predictor variables
- Recommendations for further model development
3. Sales Projections for Chemco (Capgemini)
- Capgemini challenged the team: “Beat our (multiple regression) sales prediction model, using the same data”
- Data: 12 products lines x 864 sales data points for each line x 4 global regions
- Team effort: Machine learning random forest models
- Team’s model consistently showed lower Mean-Squared Errors than the CapG model when compared to actual sales.
4. Finding the Next Watson Use Case (IBM Watson)
- Case chosen: compliance by financial institutions with federal regulations
- Problem: Dodd-Frank and Volker Rule impose 1700 pages of regulations, affecting millions of a large bank’s documents, requiring thousands of FTE’s, estimated $70b cost of compliance by all large banks over last six years
- Team proposal: Use Watson as a “Regulatory Analyst” to sift information, identify and connect info, conduct impact analysis, and make decisions on changes to comply.
- Represents huge savings in cost of compliance, improved quality and timeliness of response; could also be used by regulators to streamline regulation.
5. Multi-channel Consumer Profiling for eCommerce (WOOX Innovations)
- Provide more segmentation and profiles of potential customers for our high quality headphones
- Data: Internal data on sales efforts, such as results of 1M email sales campaign
- Team designed and initiated an analytical approach: conducted a survey (via M-Turk) of consumer brand attitudes, motivations to buy;
- Team conducted a social media analysis of perceptions of brands
- Recommendations: specific consumer segments by age, activity in social media, type of phone, etc. and next steps of marketing focus for WOOX.
6. Predicting New Product Adoption for American Apparel (Zensar)
- Sponsor challenge: “We may have people with experience, wisdom, and opinions, predicting sales of a new line of jeans. Can we do better with analytics?”
- Data: For 128 products introduced in 2013-2014, total sales by week, prices, and some other variables.
- Team explored the data: Four adoption archetypes discovered: Uniform, Blockbuster, Linear, and Stairstep; BUT nothing in the data enabled a prediction.
- Team scrambled with Zensar and AA, got social media data of consumer comments on some products in the database. Using Word Tree text analytics, plots of extracted valuation comments against subsequent sales volumes.
- Conclusion: “Social Media data provide useful insights on consumer and show correlations with sales that should be explored further.”