Evolve on the Host, Predict on the Edge: Deploying Online Neuroevolutionary Architecture Search for Cross-sectional Stock Return Prediction

Key points

• Accurate forecasting models are usually large, expensive to update online, and fixed in architecture once trained.1
• On the Pi a single champion predicts a 50-stock window in 24.6 ms and the ensemble of 40 island champions in 556 ms, far inside the daily decision cycle.1
• On four panels of US mid-cap equities over 2022--2024, reading the population as a rank-mean ensemble of island champions returns $+27.5%$ net of realised transaction costs, against $+11.3$ to $+14.8%$ for online LSTM, online GRU and monthly-retrained LSTM baselines and $+4.5%$ for the single best genome used in prior ONE-NAS work.1

Sources (1)

• [1]Evolve on the Host, Predict on the Edge: Deploying Online Neuroevolutionary Architecture Search for Cross-sectional Stock Return Prediction
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 01:19 PM

  We apply ONE-NAS, an online neuroevolutionary architecture search that evolves a population of small recurrent networks as each window of data arrives, to daily cross-sectional stock return prediction, and pilot it on a host and endpoint pipeline: the host runs the search and ships each generation's champion genomes over TCP/IP to a Raspberry Pi 4B, which predicts online.

  Accurate forecasting models are usually large, expensive to update online, and fixed in architecture once trained.

Extractive summary: sentences quoted from the sources.