Alphathon 2024

             

Point72 / Cubist provided the following question and joined the SQA and Stony Brook in judging the submissions:

 

Title:

 

Problem:

CSP is an open-source reactive stream processing library. Using CSP, create an innovative real-time streaming application that leverages multiple asynchronous data sources.

 

Expected Outcome:

A prototype of a real-time data processing application that can generate actionable insights using a variety of techniques in quantitative finance. The application should demonstrate how it handles streaming data from multiple sources as well as the usefulness and accuracy of the insights it generates.

 

Data:

Participants will have access to data and infrastructure provided by Eagle Alpha, Quant Connect, Data Bento and/or potentially other providers, including lagged order book data and lagged news feeds.

 

Evaluation:

The submissions will be evaluated based on the creativity demonstrated in leveraging CSP’s high performance features, the rigorous use of quantitative finance skills, as well as the usefulness of the outputs generated by the application.

 

AB (AllianceBernstein) provided the following question and joined the SQA and Stony Brook in judging the submissions:

 

Title:

 

Problem:

Can we use LLMs and alternative data to outperform the S&P 500?

 

Expected Outcome:

Using LLMs with and without alternative data, your study should demonstrate if and how to use LLMs in innovative ways to extract insights and forecast future returns in ways that are incrementally and demonstrably better to simpler techniques with the same data inputs, and additive to known investment styles.

 

Data:

Participants will have access to data and infrastructure provided by Eagle Alpha, Quant Connect, Data Bento and/or potentially other providers, including market and/or textual data.

 

Evaluation:

The submissions will be evaluated based on the creativity demonstrated in proving or disproving the value of LLMs in time series forecasting, the rigorousness of the methodological comparison including risk management of known investment styles and realistic market impact assumptions, as well as the practical usefulness of the output for investment management.

 

Principal Financial Group provided the following question and joined the SQA and Stony Brook in judging the submissions:

 

Title:

 

Problem:

Can ETF fund flows prove useful in forecasting future fund flows, as well as subsequent ETF, Country and Sector returns?

 

Expected Outcome:

Participants will be evaluated on the most rigorous, usable and interesting use of ETF flow data in forecasting.

 

Data:

Participants will have access to data and infrastructure provided by Eagle Alpha, Quant Connect, Data Bento and/or potentially other providers, including ETF flows, constituents, descriptions and returns by ETF Global.

 

Evaluation:

The submissions will be evaluated on the usability of the forecasts based on realistic market assumptions, proof of value-added in excess of known styles including momentum in returns and flows themselves, as well as the practical usefulness of the forecasts.

 

Optimal Portfolio Strategies will provide the following question and join the SQA and Stony Brook in judging the submissions:

Title:
Design a Long-Short Portfolio Strategy that Accurately Reflects Stock Selection Skill

Problem:
Outperformance depends on two skills: Stock Selection and Portfolio Construction. Different portfolios holding the same stocks will have different performance: Some portfolios will do a much better job of reflecting stock selection skill than others. Can you construct a portfolio that best reflects stock selection?

Expected Outcome:
A portfolio construction methodology to maximize the effect of the expected returns (alphas) on the portfolio’s performance. All portfolios should be 100% long, 100% short for 100% cash at all times (fully invested.) The portfolio should be rebalanced as you see fit, and you will be provided with a methodology to include estimated transaction and shorting costs.

Data:
Northfield Information Services will provide the required data. The initial seven year data set will include Northfield risk models at 4-week intervals, a defined universe of around 400 Mid-Cap investable assets, daily returns, and expected alphas at 4-week intervals.

Evaluation:
Submissions will initially be evaluated on creativity and innovation in building portfolios that accurately reflect stock selection skill. Participants will then be given a new data set. Contestants will be judged on the exposure of their portfolio to the alphas, as determined by their contributions to return and risk over this new data set.