(Jose) Alejandro Lopez-Lira

Contact Information

Primary Email:
joselop@wharton.upenn.edu

Research Interests: Asset Pricing, Machine Learning, Banking, Macro Finance, Financial Frictions

Links: CV, Personal Website

Research

Alejandro Lopez-Lira and Nikolai Roussanov, A machine learning-based canonical set of portfolios for testing factor models. Abstract
We use machine learning to efficiently combine a broad set of signals and produce a testing set of portfolios sorted by ex-ante estimates of expected returns. None of the well-known factor models can explain the returns of the testing set, and we observe monotonically increasing realized risk-adjusted excess returns. A long-short value-weighted portfolio produces significant realized risk-adjusted excess returns above 1\%. We also provide an even more troublesome testing set: ex-ante covariance neutral portfolios sorted on ex-ante estimates of expected returns. A long-short covariance-neutral portfolio produces a Sharpe ratio well above one and no statistically significant covariation with any of the well-known factors, posing notable challenges to both reduced-form and consumption-based asset pricing models.
Alejandro Lopez-Lira, When do we feel confident about a predictor? A Bayesian framework for time-varying predictor relevance. Abstract
I use a Bayesian econometric model with time-varying coefficients to measure when investors have enough information to conclude that a variable is useful for the prediction of stock returns. In the model, investors have epistemic uncertainty: they do not know whether a given variable is useful for prediction. The model provides a natural framework to deal with multiple hypothesis testing concerns and has a clear advantage over frequentist inference: at any point in time, we have the joint probability distribution that the variables belong in the model. I apply the model to the cross-section of returns and find that the relevance of well-known predictors changes substantially during the business cycle. A long-short portfolio constructed using the predicted values generates significant risk-adjusted returns of around 1% per month.
Alejandro Lopez-Lira, Risk Factors That Matter: Textual Analysis of Risk Disclosures for the Cross-Section of Returns. Abstract
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. The portfolios are priced in the cross-section and contain information above and beyond the commonly used multi-factor representations. A model that uses only firm identified risk factors (FIRFs) performs at least as well as traditional factor models, despite not using any information from past prices or returns.
Alejandro Lopez-Lira, Demand-Driven Risk and the Cross-Section of Expected Returns. Abstract
Firms that concentrate their activities towards goods with higher income elasticity are more exposed to demand-driven risk, since the consumption of high-consumption households is more exposed to aggregate shocks. These firms earn higher risk-adjusted equity returns. A portfolio that goes long on the most exposed firms and short on the least exposed gets an abnormal risk-adjusted annual return of 7.5%. This risk does not seem to be coming from competition. A portfolio that goes long in firms exposed to demand-driven risk and competitive pressure and short on firms not exposed to demand-driven risk nor competitive pressure earns an abnormal risk-adjusted annual return of 14%.

Teaching

Past Courses

IMPA6020 - Econ and Pub Fin
This course introduces students to key economic concepts such as scarcity, efficiency, monopolies, and other markets to investigate the notions of economic efficiency in a competitive marketplace. In addition, this course equips students to discover how efficiency is affected by distortions relevant to public policy, especially regulations, externalities, and incomplete information. From the macroeconomics side, we cover both short-run topics, long-run topics and the effects of government debt. Students in this course practice applying these principles to the range of decisions that public sector executives have to make in order to understand the trade-offs inherent in any public policy or program.

Awards And Honors

Jacobs Levy Center Research Paper Prize for best paper, 2019
WFA Cubist Systematic Strategies Ph.D. Candidate Award for Outstanding Research, 2019
BlackRock’s Applied Research Award, Finalist, 2019
Macro-Finance Society Ph.D. Student Award, 2019
Irwin Friend Doctoral Fellowship in Finance, Wharton, 2019
Best Paper, European Investment Forum Research Prize, Cambridge, 2019
Best Paper in the Investment Track, Baltimore Area Finance Conference, 2019
Jacobs Levy Equity Management Center Research Grant, Wharton, 2019
Rodney L. White Center for Financial Research Grant, Wharton, 2019
The Mack Institute for Innovation Management Research Grant, 2019
George James Term Fund Travel Award, Wharton, 2019
Jacob Levy Fellowship, Wharton, 2019
Rodney L. White Center for Financial Research Grant, Wharton, 2018
The Mack Institute for Innovation Management Research Grant, 2018

In the News

Announcing the 2019 Jacobs Levy Center Research Paper Prizes, https://jacobslevycenter.wharton.upenn.edu/research-papers/paper-prizes/ - 12/19/2019 Description
The Jacobs Levy Center Research Paper Prizes are chosen from recent additions to the Jacobs Levy Center’s working paper series. The prizes, established in 2014, include a Best Paper award of $10,000 and one or more Outstanding Paper awards of $5,000.

Best Paper: $10,000 Award
Risk Factors that Matter: Textual Analysis of Risk Disclosures for the Cross-Section of Returns
Alejandro Lopez-Lira
The European Investment Forum Prize is awarded by the Centre for Endowment Asset Management (CEAM) at Cambridge Judge Business School and FTSE Russell to Alejandro Lopez-Lira of the Wharton School at the University of Pennsylvania and Kate Suslava of Bucknell University., Cambridge Judge Business School and FTSE Russell - 08/06/2019 Description
The Centre for Endowment Asset Management (CEAM) at Cambridge Judge Business School and FTSE Russell have awarded the first European Investment Forum Research Prize to Alejandro Lopez-Lira, PhD candidate at the Wharton School at the University of Pennsylvania and Kate Suslava, Assistant Professor at Bucknell University. The awards honour high-quality and innovative research being undertaken by junior scholars globally.

Five papers were shortlisted from 67 submissions, based on their contribution to original empirical research and relevance to asset management, and the authors were invited to present at the 2019 European Investment Forum held in Cambridge 28-29 April.

The award for Best Paper, selected by a prize committee, was won by Alejandro Lopez-Lira for his paper entitled “Risk factors that matter: textual analysis of risk disclosures for the cross-section of returns”.

The award for Best Presenter, selected by the audience of more than 80 investment professionals at the European Investment Forum, was won by Dr Kate Suslava, for her paper entitled “Stiff business headwinds and unchartered economic waters: the use of euphemisms in earnings conference calls”.

https://www.jbs.cam.ac.uk/faculty-research/centres/ceam/events/european-investment-forum/
Using a Company’s Own Words to Assess Its Risks, Knowledge@Wharton - 03/22/2019 Description
When analysts or academics want to assess the risks that a company faces, they usually look at macroeconomic factors or internal firm metrics such as a declining sales trend to calculate those risks. But research from Wharton doctoral candidate Alejandro Lopez-Lira takes a different approach.

He asked this question: What if, instead of letting the outside world tell us what risks a company faces, we let the company tell us itself? After all, a company knows its business best. Lopez-Lira used machine learning to read through the annual reports of all U.S. public companies to find out which risks they identified as the most serious ones they face. And the results can be surprising.

His findings are in the paper, “Risk Factors That Matter: Textual Analysis of Risk Disclosures for the Cross-Section of Returns.” His research was supported the Mack Institute and the Rodney L. White Center for Financial Research.