Are you interested in stock predict? If yes, this article is for you and I know that some of my readers here are involved in trading. Mostly crypto-trading, but some people I know also trade stocks.
StocksNeural website uses Deep Learning to predict stock prices and their trends. They even say they can protect your assets from COVID-19 risks using AI.
Predictive models based on Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN) are at the heart of our service. StocksNeural constantly improves them, try new models, and new scientific approaches. StocksNeural believes their model is more accurate than competitors have and our service is much easier to use by either novice or experienced traders. Company representatives communicate with some of the professional quant traders, and work together to make the system better.
Following steps are present in models training:
Loading of the historical market data from the Quandl and Cryptocompare premium datasets
Data normalization
Selection of the optimal Kalman filter parameters using our innovative approach or using causal CNNs for automated feature extraction.
Smoothing of the source data with Kalman filter using optimal parameters or using causal CNNs for detecting features at different abstraction levels and generalization.
Optimization of the Recurrent Neural Network or CNN hyperparameters
Training and validation of the Recurrent Neural Network or CNN
Model backtesting
Models are being retrained on a regular basis.
Daily pipeline for models includes steps required to load and preprocess new market data, calculate model's accuracy and performance metrics and generate trading recommendations according to the forecast made and strategy parameters
And finally, here is short explanatory video: