Publications
Publications
Show Results For
- All HBS Web
(235)
- Faculty Publications (68)
Accuracy
→
- 2020
- Working Paper
Is Accounting Useful for Forecasting GDP Growth? A Machine Learning Perspective
We provide a comprehensive examination of whether, to what extent, and which accounting variables are useful for improving the predictive accuracy of GDP growth forecasts. We leverage statistical models that accommodate a broad set of (341) variables—outnumbering the... View Details
- March 2021
- Case
VideaHealth: Building the AI Factory
By: Karim R. Lakhani and Amy Klopfenstein
Florian Hillen, co-founder and CEO of VideaHealth, a startup that used artificial intelligence (AI) to detect dental conditions on x-rays, spent the early years of his company laying the groundwork for an AI factory. A process for quickly building and iterating on new... View Details
Keywords: Artificial Intelligence; Innovation and Invention; Disruptive Innovation; Technological Innovation; Information Technology; Applications and Software; Technology Adoption; Digital Platforms; Entrepreneurship; AI and Machine Learning; Technology Industry; Medical Devices and Supplies Industry; North and Central America; United States; Massachusetts; Cambridge
- 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
- 2021
- Working Paper
Entrepreneurial Learning and Strategic Foresight
By: Aticus Peterson and Andy Wu
We study how learning by experience across projects affects an entrepreneur's strategic foresight. In a quantitative study of 314 entrepreneurs across 722 crowdfunded projects supplemented with a program of qualitative interviews, we counterintuitively find that... View Details
- 2020
- Working Paper
Algorithm-Augmented Work and Domain Experience: The Countervailing Forces of Ability and Aversion
By: Ryan Allen and Prithwiraj Choudhury
Past research offers mixed perspectives on whether domain experience helps or hurts algorithm-augmented work performance. To reconcile these perspectives, we theorize that domain experience affects algorithm-augmented performance via two distinct countervailing... View Details
- September 2020
- Article
Analyst Forecast Bundling
By: Michael Drake, Peter Joos, Joseph Pacelli and Brady Twedt
Changing economic conditions over the past two decades have created incentives for sell-side analysts to both provide their institutional clients tiered services and to streamline their written research process. One manifestation of these changes is an increased... 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
- 2021
- Working Paper
Time and the Value of Data
By: Ehsan Valavi, Joel Hestness, Newsha Ardalani and Marco Iansiti
Managers often believe that collecting more data will continually improve the accuracy of their machine learning models. However, we argue in this paper that when data lose relevance over time, it may be optimal to collect a limited amount of recent data instead of... View Details
- August 2020 (Revised March 2021)
- Case
Migros Turkey: Scaling Online Operations (A)
By: Antonio Moreno and Gamze Yucaoglu
The case opens in November 2019 as Ozgur Tort and Mustafa Bartin, CEO and chief large-format and online retail officer of Migros Ticaret A.S. (Migros), Turkey’s oldest and one of its largest supermarket chains, are contemplating what the best fulfillment format and... View Details
- Article
Oracle Efficient Private Non-Convex Optimization
By: Seth Neel, Aaron Leon Roth, Giuseppe Vietri and Zhiwei Steven Wu
One of the most effective algorithms for differentially private learning and optimization is objective perturbation. This technique augments a given optimization problem (e.g. deriving from an ERM problem) with a random linear term, and then exactly solves it.... View Details
- 2021
- Conference Presentation
An Algorithmic Framework for Fairness Elicitation
By: Christopher Jung, Michael J. Kearns, Seth Neel, Aaron Leon Roth, Logan Stapleton and Zhiwei Steven Wu
We consider settings in which the right notion of fairness is not captured by simple mathematical definitions (such as equality of error rates across groups), but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders.... View Details
- June 2020
- Article
How Scheduling Can Bias Quality Assessment: Evidence from Food Safety Inspections
By: Maria Ibanez and Michael W. Toffel
Accuracy and consistency are critical for inspections to be an effective, fair, and useful tool for assessing risks, quality, and suppliers—and for making decisions based on those assessments. We examine how inspector schedules could introduce bias that erodes... View Details
- Article
Human Capital and the Future of Work: Implications for Investors and ESG Integration
By: Sakis Kotsantonis and George Serafeim
Human capital development (HCD) is a key consideration for most companies, but only recently have investors focused on understanding the risks and opportunities related to human capital with the emergence of environmental, social, and governance (ESG) investment... View Details
- Mar 2020
- Conference Presentation
A New Analysis of Differential Privacy's Generalization Guarantees
By: Christopher Jung, Katrina Ligett, Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi and Moshe Shenfeld
We give a new proof of the "transfer theorem" underlying adaptive data analysis: that any mechanism for answering adaptively chosen statistical queries that is differentially private and sample-accurate is also accurate out-of-sample. Our new proof is elementary and... View Details
- 2020
- Article
Fast Exact Matrix Completion: A Unified Optimization Framework for Matrix Completion
By: Dimitris Bertsimas and Michael Lingzhi Li
We formulate the problem of matrix completion with and without side information as a non-convex optimization problem. We design fastImpute based on non-convex gradient descent and show it converges to a global minimum that is guaranteed to recover closely the... View Details
Keywords: Mathematical Methods
- January 2020
- Article
The Job Rating Game: Revolving Doors and Analyst Incentives
By: Elisabeth Kempf
Investment banks frequently hire analysts from rating agencies. While many argue that this "revolving door" creates captured analysts, it can also create incentives to improve accuracy. To study this issue, I construct an original dataset, linking analysts to their... View Details
- September 2019
- Article
The Interpersonal Costs of Dishonesty: How Dishonest Behavior Reduces Individuals' Ability to Read Others' Emotions
By: J.J. Lee, H. Hardin, B. Parmar and F. Gino
In this research, we examine the unintended consequences of dishonest behavior for one’s interpersonal abilities and subsequent ethical behavior. Specifically, we unpack how dishonest conduct can reduce one’s generalized empathic accuracy—the ability to accurately read... View Details
- August 2019
- Article
When and How to Diversify—A Multicategory Utility Model for Personalized Content Recommendation
By: Yicheng Song, Nachiketa Sahoo and Elie Ofek
Sometimes we desire change, a break from the same or an opportunity to fulfill different aspects of our needs. Noting that consumers seek variety, several approaches have been developed to diversify items recommended by personalized recommender systems. However,... View Details
- 2024
- Working Paper
Mammography - Early Detection, Precise Diagnoses: Case Histories of Transformational Advances
By: Amar Bhidé, Srikant M. Datar and Katherine Stebbins
This case history describes how the development of x-ray-based techniques and equipment (“mammography”) led to widespread screening for breast cancer and enabled “minimally invasive” biopsies of breast tumors. Specifically, we chronicle how: 1) new protocols and... View Details
- Article
Use of Crowd Innovation to Develop an Artificial Intelligence-Based Solution for Radiation Therapy Targeting
By: Raymond H. Mak, Michael G. Endres, Jin Hyun Paik, Rinat A. Sergeev, Hugo Aerts, Christopher L. Williams, Karim R. Lakhani and Eva C. Guinan
Importance: Radiation therapy (RT) is a critical cancer treatment, but the existing radiation oncologist work force does not meet growing global demand. One key physician task in RT planning involves tumor segmentation for targeting, which requires substantial... View Details