Machine learning

This paper investigates whether longer historical training periods improve the out-of-sample performance of a Hidden Markov Model (HMM) used for identifying financial market regimes. Four four-state Gaussian HMMs are compared, differing only in the starting point of their training data (1970, 1980, 1990, and 2000), while being evaluated on the same test period. The model uses five market-based features capturing volatility, drawdowns, credit conditions, and sector rotation to identify latent risk regimes.

The study highlights that validation methodology and evaluation criteria are as important as model design and data length when assessing regime-based investment models.

Meme stocks are commonly studied through social-media activity, but this approach limits both the historical scope of research and the signals available to practitioners. In A Century of Meme Stocks and the Price of Coordination, Chad Schmerling develops an alternative: a machine-learning model trained to identify the holdings of the Roundhill MEME ETF using market and firm-level data rather than textual inputs. By adapting the feature set to historical data availability, the paper constructs a measure of “memeness” extending back to 1926. For traders and portfolio managers, its principal contribution is a framework for identifying speculative activity and examining how its return implications vary with the investment horizon.

The integration of artificial intelligence into algorithmic trading has ignited a race to transform generative text into systematic alpha. A new paper written by Steven Edwards empirically investigates whether constructing a synthetic consensus using large language models can simulate information aggregation dynamics or if it merely acts as a sophisticated echo chamber. By utilizing an expansive framework to evaluate portfolio construction across distinct synthetic mandates, the study challenges whether generative agents can truly democratize the wisdom of crowds within highly efficient capital markets.

Recent interesting research from Cakici and Zaremba, highlights an often-overlooked aspect of machine learning for equity return prediction: the choice of prediction target. Rather than focusing on increasingly sophisticated model architectures or feature engineering, the authors show that how returns are represented during training has a much larger impact on predictive performance. In particular, models trained to predict stock ranks instead of raw return levels generate substantially stronger portfolio performance—roughly doubling both returns and Sharpe ratios in large-cap universes.

Large language models are already capable of summarizing financial research, but are they ready to conduct it? In their latest paper, researchers from Google, Boston College, and Columbia introduce a framework where a large language model doesn’t just fetch data—it acts as an autonomous AI research agent capable of navigating the “hypothesis discovery loop.” By placing an LLM within a human-designed laboratory—complete with a symbolic language of 66 accounting primitives and a standardized backtesting pipeline—the authors tested whether AI can move beyond black-box predictions to generate economically legible and statistically robust signals. This isn’t just about throwing a transformer at a price series; it is a systematic attempt to automate the “propose–test–reflect” cycle that defines empirical finance.

Artificial intelligence is gradually changing the way quantitative researchers interact with financial data. Instead of manually browsing databases, comparing strategies one by one and filtering spreadsheets, modern research workflows increasingly rely on conversational systems capable of retrieving and summarizing structured information automatically.

One practical application is combining the Quantpedia API with an LLM such as ChatGPT, Claude or Cursor AI to create a lightweight quant research assistant. In this setup, Quantpedia API provides structured access to quantitative trading strategies, performance metrics, classifications, equity curves, trading codes, and related research metadata through the official Quantpedia API, while the LLM acts as a conv