Publications
Publications
Show Results For
- All HBS Web
(330)
- Faculty Publications (79)
- 2022
- Working Paper
TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations
By: Dylan Slack, Satyapriya Krishna, Himabindu Lakkaraju and Sameer Singh
Practitioners increasingly use machine learning (ML) models, yet they have become more complex and harder to understand. To address this issue, researchers have proposed techniques to explain model predictions. However, practitioners struggle to use explainability... View Details
- 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
- Article
Counterfactual Explanations Can Be Manipulated
By: Dylan Slack, Sophie Hilgard, Himabindu Lakkaraju and Sameer Singh
Counterfactual explanations are useful for both generating recourse and auditing fairness between groups. We seek to understand whether adversaries can manipulate counterfactual explanations in an algorithmic recourse setting: if counterfactual explanations indicate... View Details
- September 15, 2021
- Article
Improving Deconvolution Methods in Biology Through Open Innovation Competitions: An Application to the Connectivity Map
By: Andrea Blasco, Ted Natoli, Michael G. Endres, Rinat A. Sergeev, Steven Randazzo, Jin Hyun Paik, N.J. Maximilian Macaluso, Rajiv Narayan, Xiaodong Lu, David Peck, Karim R. Lakhani and Aravind Subramanian
A recurring problem in biomedical research is how to isolate signals of distinct populations (cell types, tissues, and genes) from composite measures obtained by a single analyte or sensor. Existing computational deconvolution approaches work well in many specific... View Details
- August 2021
- Article
Crowdsourcing Memories: Mixed Methods Research by Cultural Insiders-Epistemological Outsiders
By: Tarun Khanna, Karim R. Lakhani, Shubhangi Bhadada, Nabil Khan, Saba Kohli Davé, Rasim Alam and Meena Hewett
This paper examines the role that the two lead authors’ personal connections played in the research methodology and data collection for the Partition Stories Project—a mixed-methods approach to revisiting the much-studied historical trauma of the Partition of British... View Details
- Article
Learning Models for Actionable Recourse
By: Alexis Ross, Himabindu Lakkaraju and Osbert Bastani
As machine learning models are increasingly deployed in high-stakes domains such as legal and financial decision-making, there has been growing interest in post-hoc methods for generating counterfactual explanations. Such explanations provide individuals adversely... View Details
- Article
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations
By: Sushant Agarwal, Shahin Jabbari, Chirag Agarwal, Sohini Upadhyay, Steven Wu and Himabindu Lakkaraju
As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniques for explaining these black boxes in a post hoc manner. In this work, we analyze two... View Details
- 2020
- Working Paper
Is Accounting Useful for Forecasting GDP Growth? A Machine Learning Perspective
We provide a comprehensive examination of whether, to what extent, and which accounting variables are useful for improving the predictive accuracy of GDP growth forecasts. We leverage statistical models that accommodate a broad set of (341) variables—outnumbering the... View Details
- Mar 2021
- Conference Presentation
Descent-to-Delete: Gradient-Based Methods for Machine Unlearning
By: Seth Neel, Aaron Leon Roth and Saeed Sharifi-Malvajerdi
We study the data deletion problem for convex models. By leveraging techniques from convex optimization and reservoir sampling, we give the first data deletion algorithms that are able to handle an arbitrarily long sequence of adversarial updates while promising both... View Details
- 2021
- Working Paper
First Law of Motion: Influencer Video Advertising on TikTok
By: Jeremy Yang, Juanjuan Zhang and Yuhan Zhang
This paper engineers an intuitive feature that is predictive of the causal effect of influencer video advertising on product sales. We propose the concept of m-score, a summary statistic that captures the extent to which a product is advertised in the most engaging... View Details
- February 2021
- Tutorial
Assessing Prediction Accuracy of Machine Learning Models
By: Michael Toffel and Natalie Epstein
This video describes how to assess the accuracy of machine learning prediction models, primarily in the context of machine learning models that predict binary outcomes, such as logistic regression, random forest, or nearest neighbor models. After introducing and... View Details
- February 2021
- Tutorial
What is AI?
By: Tsedal Neeley
This video explores the elements that constitute artificial intelligence (AI). From its mathematical basis to current advances in AI, this video introduces students to data, tools, and statistical models that make a computer 'intelligent.' Through an explanation of... View Details
- Article
Resilience vs. Vulnerability: Psychological Safety and Reporting of Near Misses with Varying Proximity to Harm in Radiation Oncology
By: Palak Kundu, Olivia Jung, Amy C. Edmondson, Nzhde Agazaryan, John Hegde, Michael Steinberg and Ann Raldow
Background
Psychological safety, a shared belief that interpersonal risk taking is safe, is an important determinant of incident reporting. However, how psychological safety affects near-miss reporting is unclear, as near misses contain contrasting cues that... View Details
Psychological safety, a shared belief that interpersonal risk taking is safe, is an important determinant of incident reporting. However, how psychological safety affects near-miss reporting is unclear, as near misses contain contrasting cues that... View Details
- September 2020 (Revised March 2022)
- Case
JOANN: Joannalytics Inventory Allocation Tool
By: Kris Ferreira and Srikanth Jagabathula
Michael Joyce, Vice President of Inventory Management at JOANN, championed an effort to develop and implement an inventory allocation analytics tool that used advanced analytics to predict in-season demand of seasonal items for each of JOANN’s nearly 900 stores and... View Details
Keywords: Analytics; Machine Learning; Optimization; Inventory Management; Mathematical Methods; Decision Making; Operations; Supply Chain Management; Resource Allocation; Distribution; Technology Adoption; Applications and Software; Change Management; Fashion Industry; Consumer Products Industry; Retail Industry; United States; Ohio
- August 2020 (Revised September 2020)
- Technical Note
Assessing Prediction Accuracy of Machine Learning Models
The note introduces a variety of methods to assess the accuracy of machine learning prediction models. The note begins by briefly introducing machine learning, overfitting, training versus test datasets, and cross validation. The following accuracy metrics and tools... View Details
- Article
Oracle Efficient Private Non-Convex Optimization
By: Seth Neel, Aaron Leon Roth, Giuseppe Vietri and Zhiwei Steven Wu
One of the most effective algorithms for differentially private learning and optimization is objective perturbation. This technique augments a given optimization problem (e.g. deriving from an ERM problem) with a random linear term, and then exactly solves it.... View Details
- 2021
- Conference Presentation
An Algorithmic Framework for Fairness Elicitation
By: Christopher Jung, Michael J. Kearns, Seth Neel, Aaron Leon Roth, Logan Stapleton and Zhiwei Steven Wu
We consider settings in which the right notion of fairness is not captured by simple mathematical definitions (such as equality of error rates across groups), but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders.... View Details
- Mar 2020
- Conference Presentation
A New Analysis of Differential Privacy's Generalization Guarantees
By: Christopher Jung, Katrina Ligett, Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi and Moshe Shenfeld
We give a new proof of the "transfer theorem" underlying adaptive data analysis: that any mechanism for answering adaptively chosen statistical queries that is differentially private and sample-accurate is also accurate out-of-sample. Our new proof is elementary and... View Details
- Article
Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error
By: Celia Cintas, Skyler Speakman, Victor Akinwande, William Ogallo, Komminist Weldemariam, Srihari Sridharan and Edward McFowland III
Reliably detecting attacks in a given set of inputs is of high practical relevance because of the vulnerability of neural networks to adversarial examples. These altered inputs create a security risk in applications with real-world consequences, such as self-driving... View Details
- Article
Machine Learning Approaches to Facial and Text Analysis: Discovering CEO Oral Communication Styles
By: Prithwiraj Choudhury, Dan Wang, Natalie A. Carlson and Tarun Khanna
We demonstrate how a novel synthesis of three methods—(1) unsupervised topic modeling of text data to generate new measures of textual variance, (2) sentiment analysis of text data, and (3) supervised ML coding of facial images with a cutting-edge convolutional neural... View Details