Publications

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

A key policy question raised by the advent of fintech lenders revolves around the impact on credit availability of credit models that employ alternative data and algorithmic underwriting. We exploit anonymized administrative data provided by a major fintech platform... View Details

12 Jan 2023
News

‘Debiasing’ Debt with Data

aspects of that data might create bias, then you absolutely will not build your algorithm with intentionality.” Ballard decided to field-test his idea on another underserved business population: the... View Details

Keywords: Ralph Ranalli

September 2020 (Revised June 2023)
Exercise

Artea: Designing Targeting Strategies

By: Eva Ascarza and Ayelet Israeli

This collection of exercises aims to teach students about 1)Targeting Policies; and 2)Algorithmic bias in marketing—implications, causes, and possible solutions. Part (A) focuses on A/B testing analysis and targeting. Parts (B),(C),(D) Introduce algorithmic bias. The... View Details

2021
Article

Does Fair Ranking Improve Minority Outcomes? Understanding the Interplay of Human and Algorithmic Biases in Online Hiring

By: Tom Sühr, Sophie Hilgard and Himabindu Lakkaraju

Ranking algorithms are being widely employed in various online hiring platforms including LinkedIn, TaskRabbit, and Fiverr. Prior research has demonstrated that ranking algorithms employed by these platforms are prone to a variety of undesirable biases, leading to the... View Details

October 2022
Exercise

Shanty Real Estate: Updated Confidential Information for iBuyer

By: Michael Luca, Jesse M. Shapiro and Nathan Sun

Shanty is a simulation in which students inhabit the role of either a traditional home buyer or an iBuyer, both bidding on the same condo. The traditional home buyer has access to a “comp sheet” of similar properties that have recently sold, and has done a walkthrough.... View Details

Keywords: Algorithm; Decision Choices and Conditions; Measurement and Metrics; Market Timing; Decision Making

April 2024
Article

A Machine Learning Algorithm Predicting Risk of Dilating VUR among Infants with Hydronephrosis Using UTD Classification

By: Hsin-Hsiao Scott Wang, Michael Lingzhi Li, Dylan Cahill, John Panagides, Tanya Logvinenko, Jeanne Chow and Caleb Nelson

Backgrounds: Urinary Tract Dilation (UTD) classification has been designed to be a more objective grading system to evaluate antenatal and post-natal UTD. Due to unclear association between UTD classifications to specific anomalies such as vesico-ureteral reflux (VUR),... View Details

Keywords: Health Disorders; Health Testing and Trials; AI and Machine Learning; Health Industry

2017
Working Paper

Nowcasting the Local Economy: Using Yelp Data to Measure Economic Activity

By: Edward L. Glaeser, Hyunjin Kim and Michael Luca

Can new data sources from online platforms help to measure local economic activity? Government datasets from agencies such as the U.S. Census Bureau provide the standard measures of economic activity at the local level. However, these statistics typically appear only... View Details

Keywords: Economy; Analytics and Data Science; Local Range; Social and Collaborative Networks

SSRN

October 2022
Exercise

Shanty Real Estate: Confidential Information for iBuyer 3

By: Michael Luca, Jesse M. Shapiro and Nathan Sun

Shanty is a simulation in which students inhabit the role of either a traditional home buyer or an iBuyer, both bidding on the same condo. The traditional home buyer has access to a “comp sheet” of similar properties that have recently sold, and has done a walkthrough.... View Details

Keywords: Algorithm; Decision Choices and Conditions; Decision Making; Measurement and Metrics; Market Timing

October 2022
Exercise

Shanty Real Estate: Updated Confidential Information for Homebuyer

By: Michael Luca, Jesse M. Shapiro and Nathan Sun

Shanty is a simulation in which students inhabit the role of either a traditional home buyer or an iBuyer, both bidding on the same condo. The traditional home buyer has access to a “comp sheet” of similar properties that have recently sold, and has done a walkthrough.... View Details

Keywords: Algorithm; Decision Choices and Conditions; Decision Making; Market Timing; Measurement and Metrics

Teaching Interest

Overview

Paul is primarily interested in teaching data science to management students through the case method. This includes technical topics (programming and statistics) as well as higher-level management issues (digital transformation, data governance, etc.) As a research... View Details

Keywords: A/B Testing; AI; AI Algorithms; AI Creativity; Algorithm; Algorithm Bias; Algorithmic Bias; Algorithmic Fairness; Algorithms; Analytics; Application Program Interface; Artificial Intelligence; Causality; Causal Inference; Computing; Computers; Data Analysis; Data Analytics; Data Architecture; Data As A Service; Data Centers; Data Governance; Data Labeling; Data Management; Data Manipulation; Data Mining; Data Ownership; Data Privacy; Data Protection; Data Science; Data Science And Analytics Management; Data Scientists; Data Security; Data Sharing; Data Strategy; Data Visualization; Database; Data-driven Decision-making; Data-driven Management; Data-driven Operations; Datathon; Economics Of AI; Economics Of Innovation; Economics Of Information System; Economics Of Science; Forecast; Forecast Accuracy; Forecasting; Forecasting And Prediction; Information Technology; Machine Learning; Machine Learning Models; Prediction; Prediction Error; Predictive Analytics; Predictive Models; Analysis; AI and Machine Learning; Analytics and Data Science; Applications and Software; Digital Transformation; Information Management; Digital Strategy; Technology Adoption

May 2020
Article

Inventory Auditing and Replenishment Using Point-of-Sales Data

By: Achal Bassamboo, Antonio Moreno and Ioannis Stamatopoulos

Spoilage, expiration, damage due to employee/customer handling, employee theft, and customer shoplifting usually are not reflected in inventory records. As a result, records often report phantom inventory, i.e., units of good not available for sale. We derive an... View Details

Keywords: Shelf Availability; Inventory Record Inaccuracy; Optimal Replenishment; Retail Analytics; Performance Effectiveness; Analysis; Mathematical Methods

Find at Harvard

May 2018
Article

Nowcasting Gentrification: Using Yelp Data to Quantify Neighborhood Change

By: Edward L. Glaeser, Hyunjin Kim and Michael Luca

Data from digital platforms have the potential to improve our understanding of gentrification and enable new measures of how neighborhoods change in close to real time. Combining data on businesses from Yelp with data on gentrification from the Census, Federal Housing... View Details

Keywords: Forecasting Models; Simulation Methods; Regional Economic Activity: Growth, Development, Environmental Issues, And Changes; Geographic Location; Local Range; Transition; Analytics and Data Science; Measurement and Metrics; Economic Growth; Forecasting and Prediction

Find at Harvard

October 2022
Exercise

Shanty Real Estate: Confidential Information for iBuyer 1

By: Michael Luca, Jesse M. Shapiro and Nathan Sun

Shanty is a simulation in which students inhabit the role of either a traditional home buyer or an iBuyer, both bidding on the same condo. The traditional home buyer has access to a “comp sheet” of similar properties that have recently sold, and has done a walkthrough.... View Details

Keywords: Algorithm; Decision Choices and Conditions; Decision Making; Measurement and Metrics; Market Timing

May–June 2023
Article

Analytics for Marketers: When to Rely on Algorithms and When to Trust Your Gut

By: Fabrizio Fantini and Das Narayandas

Advanced analytics can help companies solve a host of management problems, including those related to marketing, sales, and supply-chain operations, which can lead to a sustainable competitive advantage. But as more data becomes available and advanced analytics are... View Details

Keywords: Analytics and Data Science; Decision Making

Register to Read

27 Jul 2017
News

The Revolution in Advertising: From Don Draper to Big Data

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

Keywords: Machine Learning; Unlearning Algorithm; Mathematical Methods