Skip to content

Real-time prediction of cognitive fatigue using LSTM models and simulated trading behavior

Notifications You must be signed in to change notification settings

Zoha-Arif/PredictingCognitiveFatigueInStockTrading

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

8 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

๐Ÿง  Predicting Cognitive Fatigue in Stock Trading

This project uses a neural network model to predict cognitive fatigue in simulated stock trading behavior based on decision-making patterns and reaction times. It combines time-series processing, deep learning, and trading simulation to explore how fatigue may manifest in behavioral data.

The goal was to build a real-time fatigue detection system that analyzes:

  • Reaction time consistency
  • Trading decisions over time (BUY, SELL, HOLD)
  • Sequence patterns leading to mental fatigue

๐Ÿง  Features

  • FatigueLSTM model: Custom LSTM-based neural network built using PyTorch
  • Real-time fatigue prediction using rolling windows
  • Simulated trader environment for generating or testing behavioral data
  • Behavioral encoding of decisions for model compatibility
  • Configurable sequence length and model hyperparameters

๐Ÿ“ Repository Structure

File Description
fatigue_model.pt Pretrained PyTorch model weights
predict_live.py Real-time prediction using the trained model
prepare_sequences.py Sequence preprocessing for time-series input
train_model.py Training script for LSTM using session data
trader_simulator.py Simulates trading sessions with reaction times and choices
requirements.txt Python dependencies

๐Ÿ›  Tech Stack

  • Python
  • PyTorch
  • pandas, NumPy
  • Matplotlib (optional for plotting, not shown in repo yet)

About

Real-time prediction of cognitive fatigue using LSTM models and simulated trading behavior

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages