Filter Results:
(108)
Show Results For
- All HBS Web (148)
- Faculty Publications (34)
Show Results For
- All HBS Web (148)
- Faculty Publications (34)
Sort by
- October–December 2022
- Article
Achieving Reliable Causal Inference with Data-Mined Variables: A Random Forest Approach to the Measurement Error Problem
By: Mochen Yang, Edward McFowland III, Gordon Burtch and Gediminas Adomavicius
Combining machine learning with econometric analysis is becoming increasingly prevalent in both research and practice. A common empirical strategy involves the application of predictive modeling techniques to "mine" variables of interest from available data, followed... View Details
Keywords: Machine Learning; Econometric Analysis; Instrumental Variable; Random Forest; Causal Inference; AI and Machine Learning; Forecasting and Prediction
Yang, Mochen, Edward McFowland III, Gordon Burtch, and Gediminas Adomavicius. "Achieving Reliable Causal Inference with Data-Mined Variables: A Random Forest Approach to the Measurement Error Problem." INFORMS Journal on Data Science 1, no. 2 (October–December 2022): 138–155.
- 01 Oct 2001
- Research & Ideas
How To Make Restructuring Work for Your Company
objective. Combining the two banks created opportunities to eliminate overlaps in such areas as back-office staff, branch offices, and computing infrastructure. Management of both banks also believed that larger and more diversified... View Details
Keywords: by Stuart C. Gilson
- 14 Mar 2023
- In Practice
What Does the Failure of Silicon Valley Bank Say About the State of Finance?
on SVB, and the subsequent run on other regional banks. Many observers postulate that the vulnerability was hiding in plain sight (an unsettling thought), a result of a combination of COVID government stimulus followed by a series of... View Details
- 17 Sep 2012
- Research & Ideas
Blue Skies, Distractions Arise: How Weather Affects Productivity
To The Lab With that supporting data in hand, the team decided to test the weather/productivity connection in the controlled setting of a research lab. The goal was to establish causality for the correlative findings. "I love when you View Details
Keywords: by Carmen Nobel
- 15 Jul 2019
- Book
Many Executives Are Afraid of Finance. Here's How They Can Gain Confidence
being possibly regulated as a publisher, and many, many other things! Unsurprisingly, people get valuations wrong all the time. That’s part of what makes finance so much fun and so interesting. People’s forecasts will differ, and... View Details
Keywords: by Dina Gerdeman
- 13 Nov 2019
- Research & Ideas
Don't Turn Your Marketing Function Over to AI Just Yet
practice. “We propose to step back and ask how we can best integrate machine learning to solve previously untenable marketing problems facing real companies?” Combining man and machine A product of the 11th Triennial Invitational Choice... View Details
Keywords: by Kristen Senz
- 21 Aug 2019
- Research & Ideas
What Machine Learning Teaches Us about CEO Leadership Style
expressions of chief executives to see if leadership style can be correlated with a firm’s performance. The researchers believe their work could open new directions in big data analysis, combining image and textual analysis to create a... View Details
Keywords: by Michael Blanding
- 23 May 2018
- Research & Ideas
How to Know If Your Neighborhood Is Being Gentrified
Luca, Harvard University Economics Professor Edward L. Glaeser, and HBS doctoral student Hyunjin Kim. The researchers combined data from US Census reports, the Federal Housing Finance Agency, Google Street View, and Yelp to explore... View Details
Keywords: by Dina Gerdeman
- 03 Oct 2005
- Research & Ideas
The Box Office Power of Stars
can help to attract audiences to the film. Their power may find its origins in superior acting skills, a loyal fan base, a knack for picking the most promising projects, a strong relationship with other creative talent, a solid box-office record, or a View Details
- 10 Oct 2011
- Research & Ideas
Retailing Revolution: Category Killers on the Brink
the web. Given that the forecast for total retail sales over the next several years is flat to minimal growth after inflation, any sales that occur online will be at the expense of in-store sales. Clearly, bricks-and-mortar store... View Details
- 18 Jul 2019
- Lessons from the Classroom
The Internet of Things Needs a Business Model. Here It Is
sensors can be combined with weather forecasting to help energy companies figure out the optimal amount of electricity they should sell into the grid. “Very little human intervention is needed,” Lal says.... View Details
- 24 Sep 2020
- Research & Ideas
Financial Meltdowns Are More Predictable Than We Thought
household debt were growing quickly. That combination is “a natural signal of an outward shift in the supply of credit, which then sows the seeds of its own destruction,” the researchers write in their working paper Predictable Financial... View Details
- 16 Oct 2018
- First Look
New Research and Ideas, October 16, 2018
input more valuable. Distributed supermodular complementarity (DSMC) exists when two or more independent actors can create complementary value by pursuing their own interests and will not find it advantageous to combine in order to... View Details
Keywords: Dina Gerdeman
- 06 May 2015
- What Do You Think?
Are You Ready for Personalized Predictive Analytics?
Summing Up Personal Predictive Analytics: Should We Be Careful What We Wish For? The world of continuous monitoring of numerous sensors for machines and humans, limitless information storage capacity, and big data combined with rapid... View Details
Keywords: by James Heskett
- 09 Dec 2015
- Research Event
How Do You Predict Demand and Set Prices For Products Never Sold Before?
predictive and prescriptive analytics can be combined to develop a tactical decision-making tool that makes a big impact on the bottom line. For details about the research and the successful machine learning tool, see the paper “Analytics... View Details
- 28 Oct 2024
- Op-Ed
Latino Voters Have Grown More Politically Divided. That’s Not Surprising.
asked, if each group voted like they did in the last election, who would win the next one? “Our analysis of data combining voters’ opinions with party platforms showed that where voters lead, parties tend to follow.” It turns out that... View Details
- 11 Apr 2017
- First Look
First Look at New Research, April 11
forthcoming Journal of Accounting & Economics Career Concerns of Banking Analysts By: Horton, Joanne, George Serafeim, and Shan Wu Abstract—We study how career concerns influence banking analysts' forecasts and how their View Details
- 01 Jul 2014
- First Look
First Look: July 1
firm-level expected returns and expected profitability are time-varying but highly persistent; 2) forecasts of holding period returns strongly predict the cross section of future returns up to three years ahead. We document a highly... View Details
Keywords: Carmen Nobel
- 14 Apr 2009
- First Look
First Look: April 14, 2009
these settings. In this paper we set out to accomplish both tasks by investigating the implementation of a lean production system at an Indian software services firm. Combining a detailed case study and empirical analysis we document the... View Details
Keywords: Martha Lagace
- 07 Jul 2009
- First Look
First Look: July 7
Working PapersConsistency and Monotonicity in One-Sided Assignment Problems Authors:Bettina Klaus and Alexandru Nichifor Abstract One-sided assignment problems combine important features of two well-known matching models. First, as in... View Details
Keywords: Martha Lagace