Publications

Find at Harvard

August 2020 (Revised September 2020)
Technical Note

Assessing Prediction Accuracy of Machine Learning Models

By: Michael W. Toffel, Natalie Epstein, Kris Ferreira and Yael Grushka-Cockayne

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

Keywords: Machine Learning; Statistics; Econometric Analyses; Experimental Methods; Data Analysis; Data Analytics; Forecasting and Prediction; Analytics and Data Science; Analysis; Mathematical Methods

Educators

2023
Working Paper

Insufficiently Justified Disparate Impact: A New Criterion for Subgroup Fairness

By: Neil Menghani, Edward McFowland III and Daniel B. Neill

In this paper, we develop a new criterion, "insufficiently justified disparate impact" (IJDI), for assessing whether recommendations (binarized predictions) made by an algorithmic decision support tool are fair. Our novel, utility-based IJDI criterion evaluates false... View Details

Keywords: AI and Machine Learning; Forecasting and Prediction; Prejudice and Bias

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

Keywords: Machine Learning; Statistics; Experiments; Forecasting and Prediction; Performance Evaluation

24 Aug 2021
Cold Call Podcast

Why Did Pet Concierge Startup Baroo Fail?

Keywords: Re: Thomas R. Eisenmann; Technology; Service

05 Dec 2005
What Do You Think?

Is Growth Good?

an important distinction: "Granted, the ethics of growth can be two-sided, but growth should not be confused with greed. Agriculture, healthcare, and education . . . are areas of potential growth that can be positive if not tainted... View Details

Keywords: by James Heskett

26 Mar 2024
Cold Call Podcast

How Do Great Leaders Overcome Adversity?

Keywords: Re: Anthony Mayo

July 2023 (Revised April 2024)
Case

Raymond Jefferson: Trial by Fire

By: Anthony Mayo and Carin-Isabel Knoop

In the spring of 2021, Raymond (Ray) Jefferson applied for a job in President Joseph Biden’s administration. Ten years earlier, false allegations were used to force him to resign from his prior U.S. government position as Assistant Secretary of Labor for Veterans’... View Details

Keywords: Leadership Style; Personal Development and Career; Ethics; Lawsuits and Litigation

Educators

May–June 2021
Article

Why Start-ups Fail

By: Thomas R. Eisenmann

If you’re launching a business, the odds are against you: Two-thirds of start-ups never show a positive return. Unnerved by that statistic, a professor of entrepreneurship at Harvard Business School set out to discover why. Based on interviews and surveys with hundreds... View Details

Keywords: Entrepreneurship; Business Startups; Problems and Challenges; Failure

Find at Harvard

Article

Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness

By: Michael J Kearns, Seth Neel, Aaron Leon Roth and Zhiwei Steven Wu

The most prevalent notions of fairness in machine learning are statistical definitions: they fix a small collection of pre-defined groups, and then ask for parity of some statistic of the classifier (like classification rate or false positive rate) across these groups.... View Details

Keywords: Machine Learning; Algorithms; Fairness; Mathematical Methods

Article

Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs

By: Michael G. Endres, Florian Hillen, Marios Salloumis, Ahmad R. Sedaghat, Stefan M. Niehues, Olivia Quatela, Henning Hanken, Ralf Smeets, Benedicta Beck-Broichsitter, Carsten Rendenbach, Karim R. Lakhani, Max Helland and Robert A. Gaudin

Periapical radiolucencies, which can be detected on panoramic radiographs, are one of the most common radiographic findings in dentistry and have a differential diagnosis including infections, granuloma, cysts, and tumors. In this study, we seek to investigate the... View Details

Keywords: Artificial Intelligence; Diagnosis; Computer-assisted; Image Interpretation; Machine Learning; Radiography; Panoramic Radiograph; AI and Machine Learning

27 Feb 2012
Research & Ideas

When Researchers Cheat (Just a Little)

other end of the spectrum, researchers can obtain false positives by running statistical tests over and over until they find the result they are looking for, or by excluding data after looking at how doing... View Details

Keywords: by Katie Johnston; Education

14 Sep 2007
Research & Ideas

How to Profit from Scarcity

the right place at the right price. Coca-Cola's mantra always has been to be within an arm's reach of desire. To be out of stock is to lose a sale or, worse, to lose a sale to a competitor. But marketers also understand that, by using the illusion of scarcity, they can... View Details

Keywords: by John Quelch; Consumer Products; Advertising

2022
Working Paper

Slowly Varying Regression under Sparsity

By: Dimitris Bertsimas, Vassilis Digalakis Jr, Michael Lingzhi Li and Omar Skali Lami

We consider the problem of parameter estimation in slowly varying regression models with sparsity constraints. We formulate the problem as a mixed integer optimization problem and demonstrate that it can be reformulated exactly as a binary convex optimization problem... View Details

Keywords: Mathematical Methods

2019
Article

An Empirical Study of Rich Subgroup Fairness for Machine Learning

By: Michael J Kearns, Seth Neel, Aaron Leon Roth and Zhiwei Steven Wu

Kearns et al. [2018] recently proposed a notion of rich subgroup fairness intended to bridge the gap between statistical and individual notions of fairness. Rich subgroup fairness picks a statistical fairness constraint (say, equalizing false positive rates across... View Details

Keywords: Machine Learning; Fairness; AI and Machine Learning

January 2021
Case

Anodot: Autonomous Business Monitoring

By: Antonio Moreno and Danielle Golan

Autonomous business monitoring platform Anodot leveraged machine learning to provide real-time alerts regarding business anomalies. Anodot’s solution was used in various industries in order to primarily monitor business health, such as revenue and payments, product... View Details

Keywords: Digital Platforms; Internet and the Web; Knowledge Sharing; Information Management; Sales; Value Creation; Product Positioning; Israel

Educators

October 2009
Article

Managing Risk in the New World

By: Robert S. Kaplan, Anette Mikes, Robert Simons, Peter Tufano and Michael Hofmann Jr.

Five experts gathered recently to discuss the future of enterprise risk management: Kaplan, the Baker Foundation Professor at Harvard Business School, who with his colleague David Norton developed the balanced scorecard; Mikes, an assistant professor at HBS who studies... View Details

Keywords: Forecasting and Prediction; Financial Crisis; Capital Structure; Job Cuts and Outsourcing; Risk Management

Find at Harvard