Quant Science的动态

Stock Prediction AI: Using Machine Learning and Deep Learning to predict stock price movements in Python. The Python code is 100% free on GitHub. Let's dive in (bookmark this): 1. The Python Machine Learning and Deep Learning Libraries: - mxnet - gluon - sklearn - xgboost 2. Stock Price Data (Train/Test) The dashed vertical line represents the separation between training and test data. GS is shown but will use 72 assets. Daily prices for each asset. 3. Technical Indicators Analysis uses: - Moving Averages - MACD - Bollinger Bands - Momentum 4. Sentiment News The analysis uses a pretrained BERT model to classify news articles as positive or negative sentiment. 5. Fourier Transforms Used to extract global and local trends (and to de-noise) 6. ARIMA ARIMA is a forecasting method that uses lagged regression and autocorrelation. Analysis uses to extract new features and denoise. 7. XGBoost Feature Importance The analysis uses an xgboost model to create feature importances. 8. Generative Adversarial Network (GAN) The future pattern of GS's stock should be more or less the same (unless something drastically changes). GAN will allow us to generate data in the future with a similar distribution to historical data. Get the complete code here: https://lnkd.in/dWDr8TrT Want to learn how to get started with algorithmic trading with Python? Then join us on March 26th for a live webinar, how to Build Algorithmic Trading Strategies (that actually get results) Register here (500+ registered): https://lnkd.in/gysn5qza