Writing
Nothing here yet, on purpose.
The first post lands when it is worth your time. Until then, the research and external writing below is where I have already said something.
Published elsewhere
- arXiv · Jan 29, 2025
Forecasting S&P 500 Using LSTM Models
Prashant Pilla, Raji Mekonen
Compares ARIMA and LSTM networks for forecasting the S&P 500 on daily data from October 2013 to September 2024 with Bloomberg technical and macro features. The LSTM without additional features performed best, and the paper argues that sequence models handle non-linear market dependencies that linear baselines miss.
LSTM accuracy (no features): 96.41%LSTM MAE / RMSE (no features): 175.9 / 207.34LSTM accuracy (with features): 92.46% - Medium
Writing on Medium
Occasional longer-form notes on building with LLMs, Web3, and finance.