Publications
Publications
Show Results For
-
All HBS Web
(36)
- Faculty Publications (10)
Recourse
→
Page 1 of
10
Results
- 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
- 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 Robust and Reliable Algorithmic Recourse
By: Sohini Upadhyay, Shalmali Joshi and Himabindu Lakkaraju
As predictive models are increasingly being deployed in high-stakes decision making (e.g., loan
approvals), there has been growing interest in post-hoc techniques which provide recourse to affected
individuals. These techniques generate recourses under the assumption...
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
- January 2009 (Revised April 2009)
- Case
Disaster in April: The Obligations of Kelly Construction
By: John D. Macomber, Christopher M. Gordon and Ben Creo
A construction company experiences a crane accident with multiple fatalities. The CEO, a client, and an employee must make choices to meet the company's obligations. Set in 2006, the case looks at the choices faced by board members of a museum that is an important...
View Details
- March 2006
- Module Note
Finance in Weak Institutional Environments
By: Mihir A. Desai and Kathleen Luchs
Describes the sixth module in the International Finance course at Harvard Business School. The module explores the issues confronting firms that operate in weak institutional environments. The cases examine situations where investor protections are limited and how...
View Details
- December 2001 (Revised April 2003)
- Case
Financing PPL Corporation's Growth Strategy
By: Benjamin C. Esty and Carrie Ferman
PPL Corp., an electric utility in Pennsylvania, needs to finance $1 billion of peaking plants as part of its new growth strategy. In February 2001, Steve May, director of finance for PPL's Global Division, is responsible for recommending a finance plan. After...
View Details
- June 1988 (Revised December 1991)
- Case
An Tai Bao Coal Mining Project
By: W. Carl Kester and Richard P. Melnick
An Tai Bao is the world's largest open-pit coal mine and is located in China's Shanxi province. After eight years of planning and negotiating, Occidental Petroleum, the foreign partner in the deal, is about to sign an ownership and financing agreement for $475 million...
View Details
- Forthcoming
- Article
On the Privacy Risks of Algorithmic Recourse
By: Martin Pawelczyk, Himabindu Lakkaraju and Seth Neel
As predictive models are increasingly being employed to make consequential decisions, there is a growing emphasis on developing techniques that can provide algorithmic recourse to affected individuals. While such recourses can be immensely beneficial to affected...
View Details
- Forthcoming
- 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