Publications

February 2018
Article

Retention Futility: Targeting High-Risk Customers Might Be Ineffective.

By: Eva Ascarza

Companies in a variety of sectors are increasingly managing customer churn proactively, generally by detecting customers at the highest risk of churning and targeting retention efforts towards them. While there is a vast literature on developing churn prediction models... View Details

Keywords: Retention/churn; Proactive Churn Management; Field Experiments; Heterogeneous Treatment Effect; Machine Learning; Customer Relationship Management; Risk Management

08 Sep 2016
Blog Post

4 Unexpected Things I Learned at HBS

day-out with the extraordinary people who have surrounded me for the last two years. As I ready for my move to Chicago for my next adventure, I wanted to share a few things that I’ve learned during my time here. 1. I View Details

July 2019
Teaching Note

Miroglio Fashion

By: Sunil Gupta

Teaching Note for HBS Nos. 519-053, 519-070, and 519-072. View Details

Keywords: Inventory Management; Demand Forecasting; Artificial Intelligence; Machine Learning; Forecasting and Prediction; Operations; Management; Decision Making; Marketing; AI and Machine Learning; Apparel and Accessories Industry; Fashion Industry

Article

Algorithms Need Managers, Too

By: Michael Luca, Jon Kleinberg and Sendhil Mullainathan

Algorithms are powerful predictive tools, but they can run amok when not applied properly. Consider what often happens with social media sites. Today many use algorithms to decide which ads and links to show users. But when these algorithms focus too narrowly on... View Details

Keywords: Machine Learning; Algorithms; Predictive Analytics; Management; Big Data; Analytics and Data Science

Register to Read

2022
Working Paper

Product2Vec: Leveraging Representation Learning to Model Consumer Product Choice in Large Assortments

By: Fanglin Chen, Xiao Liu, Davide Proserpio and Isamar Troncoso

We propose a method, Product2Vec, based on representation learning, that can automatically learn latent product attributes that drive consumer choices, to study product-level competition when the number of products is large. We demonstrate Product2Vec’s... View Details

Keywords: Consumer Choice; Consumer Behavior; Competition; Product Marketing

SSRN

September 2014
Article

Advancing Consumer Neuroscience

By: Ale Smidts, Ming Hsu, Alan G. Sanfey, Maarten A. S. Boksem, Richard B. Ebstein, Scott A. Huettel, Joe W. Kable, Uma R. Karmarkar, Shinobu Kitayama, Brian Knutson, Israel Liberzon, Terry Lohrenz, Mirre Stallen and Carolyn Yoon

In the first decade of consumer neuroscience, strong progress has been made in understanding how neuroscience can inform consumer decision making. Here, we sketch the development of this discipline and compare it to that of the adjacent field of neuroeconomics. We... View Details

Keywords: Consumer Neuroscience; Neuroeconomics; Social Neuroscience; Genes; Machine Learning; Meta-analysis; Consumer Behavior; Decision Making; Science

September 2018 (Revised December 2019)
Case

Zebra Medical Vision

By: Shane Greenstein and Sarah Gulick

An Israeli startup founded in 2014, Zebra Medical Vision developed algorithms that produced diagnoses from X-rays, mammograms, and CT-scans. The algorithms used deep learning and digitized radiology scans to create software that could assist doctors in making... View Details

Educators

Teaching Interest

Overview

Teaching has been a lifelong passion of mine. As the third generation of academics in my family, I see good teaching as a means to give back and to encourage others to share my passion for discovery. I’ve been very lucky to have many teaching opportunities, both as an... View Details

Research Summary

Overview

By: Prithwiraj Choudhury

Prithwiraj (Raj) Choudhury is the Lumry Family Associate Professor at the Harvard Business School. He was an Assistant Professor at Wharton prior to joining Harvard. His research is focused on studying the Future of Work, especially the changing Geography of Work. In... View Details

Keywords: Geography; Mobility; Migration; Multinational; Productivity; Crucible Experiences; Machine Learning; Geographic Location; Technology Industry; India; United States; China

Article

Crowdsourcing City Government: Using Tournaments to Improve Inspection Accuracy

By: Edward Glaeser, Andrew Hillis, Scott Duke Kominers and Michael Luca

The proliferation of big data makes it possible to better target city services like hygiene inspections, but city governments rarely have the in-house talent needed for developing prediction algorithms. Cities could hire consultants, but a cheaper alternative is to... View Details

Keywords: User-generated Content; Operations; Tournaments; Policy-making; Machine Learning; Online Platforms; Analytics and Data Science; Mathematical Methods; City; Infrastructure; Business Processes; Government and Politics

August 2018 (Revised October 2020)
Case

Tailor Brands: Artificial Intelligence-Driven Branding

By: Jill Avery

Using proprietary artificial intelligence technology, startup Tailor Brands set out to democratize branding by allowing small businesses to create their brand identities by automatically generating logos in just minutes at minimal cost with no branding or design skills... View Details

Educators

04 Feb 2022
Blog Post

Learning from the Entrepreneurs-in-Residence as a Harvard MS/MBA Student

there are an infinite number of ways to spend your time learning – each equally compelling but vastly unique and tailored to various learning styles. One of the most powerful ways of View Details

15 Feb 2012
Working Paper Summaries

Learning from My Success and From Others’ Failure: Evidence from Minimally Invasive Cardiac Surgery

Keywords: by KC Diwas, Bradley R. Staats & Francesca Gino; Health

2024
Working Paper

Incrementality Representation Learning: Synergizing Past Experiments for Intervention Personalization

By: Ta-Wei Huang, Eva Ascarza and Ayelet Israeli

This paper introduces Incrementality Representation Learning (IRL), a novel multitask representation learning framework that predicts heterogeneous causal effects of marketing interventions. By leveraging past experiments, IRL efficiently designs and targets... View Details

Keywords: Heterogeneous Treatment Effect; Multi-task Learning; Representation Learning; Personalization; Promotion; Deep Learning; Field Experiments; Customer Focus and Relationships; Customization and Personalization

SSRN

April 2025
Article

Serving with a Smile on Airbnb: Analyzing the Economic Returns and Behavioral Underpinnings of the Host’s Smile

By: Shunyuan Zhang, Elizabeth Friedman, Kannan Srinivasan, Ravi Dhar and Xupin Zhang

Non-informational cues, such as facial expressions, can significantly influence judgments and interpersonal impressions. While past research has explored how smiling affects business outcomes in offline or in-store contexts, relatively less is known about how smiling... View Details

Keywords: Sharing Economy; Airbnb; Image Feature Extraction; Machine Learning; Facial Expressions; Prejudice and Bias; Nonverbal Communication; E-commerce; Consumer Behavior; Perception

10 Apr 2013
Research & Ideas

Learning Curve: Making the Most of Outsourcing

University of North Carolina at Chapel Hill. “When this type of work is outsourced it should not be viewed as a mere commodity.” Teleradiology is the reading and interpretation of CT, MRI, X-ray, and other diagnostic images. Increasingly,... View Details

Keywords: by Paul Guttry; Health

December 2018
Case

Choosy

By: Jeffrey J. Bussgang and Julia Kelley

Founded in 2017, Choosy is a data-driven fashion startup that uses algorithms to identify styles trending on social media. After manufacturing similar items using a China-based supply chain, Choosy sells them to consumers through its website and social media pages.... View Details

Educators

Article

A Prescriptive Analytics Framework for Optimal Policy Deployment Using Heterogeneous Treatment Effects

By: Edward McFowland III, Sandeep Gangarapu, Ravi Bapna and Tianshu Sun

We define a prescriptive analytics framework that addresses the needs of a constrained decision-maker facing, ex ante, unknown costs and benefits of multiple policy levers. The framework is general in nature and can be deployed in any utility maximizing context, public... View Details

Keywords: Prescriptive Analytics; Heterogeneous Treatment Effects; Optimization; Observed Rank Utility Condition (OUR); Between-treatment Heterogeneity; Machine Learning; Decision Making; Analysis; Mathematical Methods