Publications
Publications
Show Results For
-
All HBS Web
(188)
- Faculty Publications (36)
Page 1 of
36
Results
→
- 2023
- Article
On Minimizing the Impact of Dataset Shifts on Actionable Explanations
By: Anna P. Meyer, Dan Ley, Suraj Srinivas and Himabindu Lakkaraju
The Right to Explanation is an important regulatory principle that allows individuals to request actionable explanations for algorithmic decisions. However, several technical challenges arise when providing such actionable explanations in practice. For instance, models...
View Details
- 2023
- Article
Towards Bridging the Gaps between the Right to Explanation and the Right to Be Forgotten
By: Himabindu Lakkaraju, Satyapriya Krishna and Jiaqi Ma
The Right to Explanation and the Right to be Forgotten are two important principles outlined to regulate algorithmic decision making and data usage in real-world applications. While the right to explanation allows individuals to request an actionable explanation for an...
View Details
- July 2023
- Article
Design and Analysis of Switchback Experiments
By: Iavor I Bojinov, David Simchi-Levi and Jinglong Zhao
In switchback experiments, a firm sequentially exposes an experimental unit to a random treatment, measures its response, and repeats the procedure for several periods to determine which treatment leads to the best outcome. Although practitioners have widely adopted...
View Details
- 2023
- Working Paper
Design-Based Confidence Sequences: A General Approach to Risk Mitigation in Online Experimentation
By: Dae Woong Ham, Michael Lindon, Martin Tingley and Iavor Bojinov
Randomized experiments have become the standard method for companies to evaluate the performance of new products or services. In addition to augmenting managers’ decision-making, experimentation mitigates risk by limiting the proportion of customers exposed to...
View Details
- 2023
- Article
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse
By: Martin Pawelczyk, Teresa Datta, Johannes van-den-Heuvel, Gjergji Kasneci and Himabindu Lakkaraju
As machine learning models are increasingly being employed to make consequential decisions in real-world settings, it becomes critical to ensure that individuals who are adversely impacted (e.g., loan denied) by the predictions of these models are provided with a means...
View Details
- 2023
- Working Paper
Nailing Prediction: Experimental Evidence on the Value of Tools in Predictive Model Development
Predictive model development is understudied despite its centrality in modern artificial
intelligence and machine learning business applications. Although prior discussions
highlight advances in methods (along the dimensions of data, computing power, and
algorithms)...
View Details
Keywords:
Analytics and Data Science
- 2022
- Article
Data Poisoning Attacks on Off-Policy Evaluation Methods
By: Elita Lobo, Harvineet Singh, Marek Petrik, Cynthia Rudin and Himabindu Lakkaraju
Off-policy Evaluation (OPE) methods are a crucial tool for evaluating policies in high-stakes domains such as healthcare, where exploration is often infeasible, unethical, or expensive. However, the extent to which such methods can be trusted under adversarial threats...
View Details
- 2022
- Article
Towards Robust Off-Policy Evaluation via Human Inputs
By: Harvineet Singh, Shalmali Joshi, Finale Doshi-Velez and Himabindu Lakkaraju
Off-policy Evaluation (OPE) methods are crucial tools for evaluating policies in high-stakes domains such as healthcare, where direct deployment is often infeasible, unethical, or expensive. When deployment environments are expected to undergo changes (that is, dataset...
View Details
- 2022
- Conference Presentation
Towards the Unification and Robustness of Post hoc Explanation Methods
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
Keywords:
AI and Machine Learning
- Article
Reliable Post hoc Explanations: Modeling Uncertainty in Explainability
By: Dylan Slack, Sophie Hilgard, Sameer Singh and Himabindu Lakkaraju
As black box explanations are increasingly being employed to establish model credibility in high stakes settings, it is important to ensure that these explanations are accurate and reliable. However, prior work demonstrates that explanations generated by...
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
- 2021
- Working Paper
Population Interference in Panel Experiments
By: Iavor I Bojinov, Kevin Wu Han and Guillaume Basse
The phenomenon of population interference, where a treatment assigned to one experimental unit affects another experimental unit's outcome, has received considerable attention in standard randomized experiments. The complications produced by population interference in...
View Details
- Article
Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses
By: Kaivalya Rawal and Himabindu Lakkaraju
As predictive models are increasingly being deployed in high-stakes decision-making, there has been a lot of interest in developing algorithms which can provide recourses to affected individuals. While developing such tools is important, it is even more critical to...
View Details
- 2020
- Working Paper
Design and Analysis of Switchback Experiments
By: Iavor I Bojinov, David Simchi-Levi and Jinglong Zhao
In switchback experiments, a firm sequentially exposes an experimental unit to a random treatment, measures its response, and repeats the procedure for several periods to determine which treatment leads to the best outcome. Although practitioners have widely adopted...
View Details
- 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
- August 2020
- Technical Note
Comparing Two Groups: Sampling and t-Testing
This note describes sampling and t-tests, two fundamental statistical concepts.
View Details
- April 2020
- Article
Field Comparisons of Incentive-Compatible Preference Elicitation Techniques
By: Shawn A. Cole, A. Nilesh Fernando, Daniel Stein and Jeremy Tobacman
Knowledge of consumer demand is important for firms, policy makers, and economists. One common tool for incentive-compatible demand elicitation, the Becker-DeGroot-Marschak (BDM) mechanism, has been widely used in laboratory settings but rarely evaluated for...
View Details
- March 2020 (Revised March 2023)
- Module Note
The Role of Experiments in Organizations
By: Michael Luca
This note outlines the structure and content of a four-class module—The Role of Experiments in Organizations—that is designed to introduce students to the role of experimental methods in managerial decisions.
View Details
- Article
Statistical Physics of Human Cooperation
By: Matjaž Perc, Jillian J. Jordan, David G. Rand, Zhen Wang, Stefano Boccaletti and Attila Szolnoki
Extensive cooperation among unrelated individuals is unique to humans, who often sacrifice personal benefits for the common good and work together to achieve what they are unable to execute alone. The evolutionary success of our species is indeed due, to a large...
View Details
- December 2016
- Article
The Effects of Endowment Size and Strategy Method on Third Party Punishment
By: Jillian J. Jordan, Katherine McAuliffe and David G. Rand
Numerous experiments have shown that people often engage in third-party punishment (3PP) of selfish behavior. This evidence has been used to argue that people respond to selfishness with anger, and get utility from punishing those who mistreat others. Elements of the...
View Details