The Future of Investing: AI and Alternative Data in Quantitative Equity Strategies
Alternative data and machine learning are reshaping quantitative investing. In this on-demand session, Versor Investments examines how these tools move from buzzwords to a disciplined, hypothesis-driven research process. We explain what artificial intelligence, machine learning, and natural language processing actually mean for equity investors, and where each adds value. We also confront the hard parts. Financial data carries low signal-to-noise, models can overfit, and markets adapt as participants learn. The discussion then walks through how alternative data sets are sourced, evaluated, and deployed, using concrete examples such as consumer transactions, news, and company reviews. We share our analytical perspective on why a causal, scientific approach matters more than simply running data through a model. The session is built for allocators, consultants, and family offices who want a clear, technical view of how alternative signals can support uncorrelated, diversifying return streams. Watch the recording to see how the theory becomes practice.
What We Cover
- What AI, machine learning, and NLP mean in practice for equity investors, and how the terms differ
- The core challenges of applying machine learning to markets, including low signal-to-noise and overfitting
- How alternative data sets are sourced, evaluated, and deployed within a hypothesis-driven framework
- Worked examples of alternative data, from consumer transactions and news to business software reviews
- How alternative signals can be combined into a market-neutral, diversifying equity approach
Key Takeaways
- A causal hypothesis matters more than the model. Durable signals start with a clear economic reason a data set should predict returns. In our view, sourcing and framing the question well outweigh the choice of algorithm.
- Machine learning in markets is mostly about avoiding false signals. Financial data has low signal-to-noise, so models overfit easily. Careful cross-validation and disciplined retraining help separate genuine signal from noise.
- Markets adapt, so signals decay. As participants latch onto a data set, its edge erodes. Continuous research and fresh signals are needed to maintain performance, not a static model.
- Standard machine learning metrics rarely fit trading objectives. What matters is the forecast that can overcome transaction costs, often in the tails. Loss functions should reflect the trading goal, not average error.
- Diversifying across many independent signals can build uncorrelated returns. Resilience comes from breadth and independence across models, themes, and horizons, rather than any single signal family.
The Presenters
DeWayne Louis, Founding Partner, Capital Formation
DeWayne Louis joined Versor Investments as a Founding Partner and is based in New York. DeWayne has over 20 years of experience in quantitative investment strategies, investment banking, private equity and hedge funds.
Nishant Gurnani, Partner, Quantitative Researcher
Nishant leads futures and FX research at Versor Investments working closely with the Investment Committee in driving the investment research agenda across all strategies. Based in New York, Nishant operates across the full spectrum of strategy development from alpha signal generation to portfolio construction. Additionally, he plays an integral role in the Firm’s efforts in alternative data sourcing and the applications of machine learning.
Ludger Hentschel, Founding Partner, Investment Advisor
Ludger Hentschel joined Versor Investments as a Founding Partner and is based in New York. Ludger has over 20 years of experience in quantitative research and investing.
Disclaimer: Past performance is not necessarily indicative of future results. Participation in this webinar is limited to Qualified Eligible Participants (QEPs) as defined under applicable regulations. For informational purposes only. Not an offer to sell or a solicitation of any type with respect to any securities or financial products. This webinar was conducted in collaboration with Middlemark Partners.
Request Access
Disclosures
Each report prepared by Versor Investments LP (formerly “ARP Investments” herein after referred to as “Versor Investments”) and available on this site is for informational and educational purposes only, is not intended to be relied on as a forecast, research or investment advice, and does not constitute a recommendation, offer or solicitation to buy or sell any securities or to adopt any investment strategy. Reliance on information in this material is at the sole risk and discretion of the reader.
No information set forth on this site constitutes a prospectus, private placement memorandum or offering circular or otherwise constitutes an offer to sell, or solicitation of any offer to buy, any securities or other investments. References to specific securities, asset classes and financial markets are for illustrative purposes only and are not intended to be and should not be interpreted as recommendations. From time to time, Versor Investments may, along with Versor Investments’ clients and/or investors, hold direct or indirect positions or have exposure to securities, asset classes and financial markets referred to in a report on this site.
Offering materials relating to investments in entities managed by Versor Investments are not available to the general public. Investment funds managed by Versor Investments are available for subscription only on the basis of the relevant prospectus or confidential private placement memorandum, which is available only to investors satisfying the applicable eligibility criteria for investment.
The information set forth on this site is not intended to provide or to constitute investment, accounting, legal or tax advice. Versor Investments’ reports do not contain information that an investor should consider, evaluate or rely on with respect to the nature, potential, value or suitability of any particular sector, geographic region, security, portfolio of securities, commodity, portfolio of commodities, currency or portfolio of currencies, transaction, investment strategy or other matter. No report set forth on this site was prepared in reference to the specific investment needs, objectives or risk tolerances of any investor or client. The views expressed in a report reflect significant assumptions and subjective judgments of Versor Investments as of the date of the report, are subject to change without prior notification and may not be updated.
Certain information has been provided by third-party sources, and while Versor Investments believes that information to be reliable, Versor Investments has not independently verified such information. As such, no warranty of accuracy or reliability is given and no responsibility arising in any other way for errors and omissions (including responsibility to any person by reason of negligence) is accepted by Versor Investments, its officers, employees or agents.
This site may contain “forward looking” information that is not purely historical in nature. Such information may include, among other things, projections and forecasts. There is no guarantee that any forecasts made will come to pass.
The information is not intended to be, nor shall it be construed as, investment advice or a recommendation of any kind. Before making any investment, prospective investors should consult their investment professionals, carefully review the risk factors and other terms disclosed in the relevant offering materials and related information and rely solely on such offering materials and related information in making any investment decision.
PAST PERFORMANCE IS NOT NECESSARILY INDICATIVE OF FUTURE RESULTS. COMMODITY INTEREST TRADING INVOLVES SUBSTANTIAL RISK OF LOSS.