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

February 2021
Article

Topic Classification of Electric Vehicle Consumer Experiences with Transformer-Based Deep Learning

By: Sooji Ha, Daniel J Marchetto, Sameer Dharur and Omar Isaac Asensio

The transportation sector is a major contributor to greenhouse gas (GHG) emissions and is a driver of adverse health effects globally. Increasingly, government policies have promoted the adoption of electric vehicles (EVs) as a solution to mitigate GHG emissions.... View Details

Keywords: Natural Language Processing; Analytics and Data Science; Environmental Sustainability; Infrastructure; Transportation; Policy

12 Dec 2014
Conference Presentation

Aspect Specific Sentiment Analysis Using Hierarchical Deep Learning

By: Himabindu Lakkaraju, Richard Socher and Chris Manning

2025
Working Paper

Dynamic Personalization with Multiple Customer Signals: Multi-Response State Representation in Reinforcement Learning

By: Liangzong Ma, Ta-Wei Huang, Eva Ascarza and Ayelet Israeli

Reinforcement learning (RL) offers potential for optimizing sequences of customer interactions by modeling the relationships between customer states, company actions, and long-term value. However, its practical implementation often faces significant challenges.... View Details

Keywords: Dynamic Policy; Deep Reinforcement Learning; Representation Learning; Dynamic Difficulty Adjustment; Latent Variable Models; Customer Relationship Management; Customer Value and Value Chain; Foreign Direct Investment; Analytics and Data Science

2020
Working Paper

Overcoming the Cold Start Problem of CRM Using a Probabilistic Machine Learning Approach

By: Eva Ascarza

The success of Customer Relationship Management (CRM) programs ultimately depends on the firm's ability to understand consumers' preferences and precisely capture how these preferences may differ across customers. Only by understanding customer heterogeneity, firms can... View Details

Keywords: Customer Management; Targeting; Deep Exponential Families; Probabilistic Machine Learning; Cold Start Problem; Customer Relationship Management; Customer Value and Value Chain; Consumer Behavior; Analytics and Data Science; Mathematical Methods; Retail Industry

October 2021
Article

Overcoming the Cold Start Problem of CRM Using a Probabilistic Machine Learning Approach

By: Nicolas Padilla and Eva Ascarza

The success of Customer Relationship Management (CRM) programs ultimately depends on the firm's ability to understand consumers' preferences and precisely capture how these preferences may differ across customers. Only by understanding customer heterogeneity, firms can... View Details

Keywords: Customer Management; Targeting; Deep Exponential Families; Probabilistic Machine Learning; Cold Start Problem; Customer Relationship Management; Programs; Consumer Behavior; Analysis

Find at Harvard

05 May 2008
Research & Ideas

Connecting with Consumers Using Deep Metaphors

language of thought and expression. It is a language that marketers must learn to speak if they are to understand and connect meaningfully with their customers. Q: How did you become fascinated by deep... View Details

Keywords: by Martha Lagace; Consumer Products

2024
Working Paper

Incrementality Representation Learning: Synergizing Past Experiments for Intervention Personalization

By: Ta-Wei Huang, Eva Ascarza and Ayelet Israeli

This paper introduces Incrementality Representation Learning (IRL), a novel multitask representation learning framework that predicts heterogeneous causal effects of marketing interventions. By leveraging past experiments, IRL efficiently designs and targets... View Details

Keywords: Heterogeneous Treatment Effect; Multi-task Learning; Representation Learning; Personalization; Promotion; Deep Learning; Field Experiments; Customer Focus and Relationships; Customization and Personalization

December 2023
Article

Self-Orienting in Human and Machine Learning

By: Julian De Freitas, Ahmet Uğuralp, Zeliha Uğuralp, Laurie Paul, Joshua B. Tenenbaum and T. Ullman

A current proposal for a computational notion of self is a representation of one’s body in a specific time and place, which includes the recognition of that representation as the agent. This turns self-representation into a process of self-orientation, a challenging... View Details

Keywords: AI and Machine Learning; Behavior; Learning

April 2011
Article

Why Leaders Don't Learn from Success

By: Francesca Gino and Gary P. Pisano

We argue that for a variety of psychological reasons, it is often much harder for leaders and organizations to learn from success than to learn from failure. Success creates three kinds of traps that often impede deep learning. The first is attribution error or the... View Details

Keywords: Learning; Innovation and Management; Leadership; Failure; Success; Performance Evaluation; Prejudice and Bias

Find at Harvard

06 Aug 2007
Research & Ideas

High Hills, Deep Poverty: Explaining Civil War in Nepal

Civil wars have been the dominant form of conflict around the world since World War II, resulting in approximately 20 million deaths. But it's not just sociologists who are diving into the roots of conflict. Increasingly, economists are examining these events to View Details

Keywords: by Martha Lagace

15 Nov 2006
Research & Ideas

Lessons Not Learned About Innovation

be rediscovered in each managerial generation (about every six years) as a fundamental way to enable new growth. But each generation seems to have forgotten or never learned the mistakes of the past, so we see classic traps repeated over... View Details

Keywords: by Sean Silverthorne

May 2022 (Revised July 2022)
Case

The Voice War Continues: Hey Google vs. Alexa vs. Siri in 2022

By: David B. Yoffie and Daniel Fisher

In 2022, after five years of pursuing a new "AI-first" strategy, Google had captured a sizeable share of the American and global markets for voice assistants. Google Assistant was used by hundreds of millions of users around the world, but Amazon retained the largest... View Details

Keywords: Strategy; Artificial Intelligence; Deep Learning; Voice Assistants; Smart Home; Market Share; Globalized Markets and Industries; Competitive Strategy; Digital Platforms; AI and Machine Learning; Technology Industry; United States

Educators

Purchase

August 2022
Article

What Makes a Good Image? Airbnb Demand Analytics Leveraging Interpretable Image Features

By: Shunyuan Zhang, Dokyun Lee, Param Vir Singh and Kannan Srinivasan

We study how Airbnb property demand changed after the acquisition of verified images (taken by Airbnb’s photographers) and explore what makes a good image for an Airbnb property. Using deep learning and difference-in-difference analyses on an Airbnb panel dataset... View Details

Keywords: Sharing Economy; Airbnb; Property Demand; Computer Vision; Deep Learning; Image Feature Extraction; Content Engineering; Property; Marketing; Demand and Consumers

Find at Harvard

Teaching Interest

Interpretability and Explainability in Machine Learning

By: Himabindu Lakkaraju

As machine learning models are increasingly being employed to aid decision makers in high-stakes settings such as healthcare and criminal justice, it is important to ensure that the decision makers correctly understand and consequent trust the functionality of these... View Details

05 Jul 2006
Working Paper Summaries

Deep Links: Business School Students’ Perceptions of the Role of Law and Ethics in Business

Keywords: by Constance E. Bagley, Gavin Clarkson & Rachel Power; Legal Services

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

Keywords: Autoencoder Networks; Pattern Detection; Subset Scanning; Computer Vision; Statistical Methods And Machine Learning; Machine Learning; Deep Learning; Data Mining; Big Data; Large-scale Systems; Mathematical Methods; Analytics and Data Science