The Prevalence and Consequences of Algorithms in Hiring: A Field Experiment

Funded Research Proposal

We conduct an audit study to measure the prevalence and impact of AI hiring applications on job applicants. We apply to thousands of jobs, treating half of our application resumes by embedding the job posting within the resume such that machines have access to the job posting text when screening candidates, but human evaluators would not. We can then evaluate if algorithmic resume screening is more likely to select resumes that are a closer match to postings. By also varying applicant race and gender, we can determine if these algorithmic selection algorithms have a differential impact on candidates from underrepresented backgrounds.Read More

A Machine Learning Approach To Likeable, and Memorable Brand Slogans

Funded Research Proposal

We propose to develop and validate a model that uses automatically extracted, high-dimensional sentence embeddings to predict the likeability and memorability of new and existing slogans.Read More

Digital Redlining and the Distributional Effects of AI-enabled Promotional Targeting

Funded Research Proposal

In recent years, firms have started to incorporate new techniques from artificial intelligence into their decision making processes. However, these techniques come with a novel set of reputational and legal risks relating to algorithmic bias and digital discrimination. Read More

Risk Factors That Matter: Textual Analysis of Risk Disclosures for the Cross-Section of Returns

Working Papers

I exploit unsupervised machine learning and natural language processing techniques to elicit the risk factors that firms themselves identify in their annual reports. I quantify the firms’ exposure to each identified risk, design an econometric test to classify them as either systematic or idiosyncratic, and construct factor mimicking portfolios that proxy for each undiversifiable source of risk.Read More

Adoption of Predictive Analytics: Impact of Model Interpretability

Funded Research Proposal

One of the most important trends in business in recent years has been the growth of Big Data and predictive analytics. The trend started with traditional analytics and the emergence of decision support systems. With advances in machine learning (ML), systems can now take in large amounts of data, learn how human decision-makers have made decisions in the past, and make decisions autonomously (achieving human-level or superhuman performance in many activities). Read More

Bias-aware AI for Human Capital Management: An Innovative Approach for Algorithmic Job Screening

Funded Research Proposal

A well-known maxim in management is that “your people are your greatest asset”. Recruitment strategies in particular have been linked to firms’ innovative capacity, emphasizing the importance of maintaining competitive advantages in HR as a key goal of effective innovation management. Read More

Advertising Content and Consumer Engagement on Social Media: Evidence from Facebook

Published Research

We describe the effect of social media advertising content on customer engagement using data from Facebook. We content-code 106,316 Facebook messages across 782 companies, using a combination of Amazon Mechanical Turk and Natural Language Processing algorithms.Read More

Using Machine Learning to Predict High-Impact General Technologies

Working Papers

Can machine learning techniques be used to predict high-impact, general technologies? We find that an ensemble of deep learning models that analyze both the text of patents as well as their bibliometric information can ex-ante identify such patents, accurately identifying 80 of the top 100 high generality patents in the hold-out sample. Read More