TradingBot
Unverified ML strategy on Indices by shivamakhauri04. BotFinder score 18 out of 100.
Stock price prediction and automated trading using Deep Reinforcement Learning and Machine Learning
Source: github
BotFinder analysis pending.
TradingBot
TradingBot Stock price prediction and automated trading using Deep Q-Network (DQN) reinforcement learning. Trains an agent to make buy/sell/hold decisions on historical stock data. Architecture This project implements a Deep Q-Network (DQN) agent for automated stock trading. The key components are: Trading Environment A custom gym-compatible environment that simulates stock trading. At each time step, the agent observes the current portfolio value and recent price change history, then selects one of three actions: - Hold (action 0): Do nothing - Buy (action 1): Purchase stock at the current price - Sell (action 2): Sell all held positions Rewards are clipped to +1 (profitable trade), -1 (unprofitable trade or selling with no positions), or 0 (hold/buy). Q-Network A fully connected neural network that maps observations to Q-values for each action. The network consists of three linear layers with ReLU activations: Training Strategy - Experience Replay: Stores past transitions in a replay buffer and samples random mini-batches for training, breaking temporal correlations - Target Networ
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)