UTSA - Spring 2022
CS3793 - Artificial Intelligence
Group 3 - Stock Market Prediction
Team Member: David Albasini, John Le, Michael Maldonado, Paula Sirisumpund
What we did: Compare effectiveness of various machine learning models’ ability to predict stock prices
Purpose:To predict if the price of an individual stock will go up or down based on technical indicators and either buy or sell that stock for a particular timeline.
Hypothesis: LSTM model would have the highest accuracy since its neural network is excellent for regression problems and widely used by automated AI traders.
Link to Source Code: https://github.com/leestorm4520/ArtificialIntelligence_UbiquantMarketPrediction
Link to Youtube Presentation: https://www.youtube.com/watch?v=d_LPzOBB_Rk
Link to Genial.io Presentation: https://view.genial.ly/626af9d2f417c30018157ac8/presentation-stock-market-prediction
References:
https://github.com/areed1192/sigma_coding_youtube/blob/master/python/python-data-science/machine-learning/random-forest/random_forest_price_prediction.ipynbhttps://machinelearningmastery.com/convert-time-series-supervised-learning-problem-python/ https://towardsdatascience.com/an-introduction-to-support-vector-regression-svr-a3ebc1672c2 https://www.kaggle.com/code/ehsandahesh/stock-market-predict-volume-with-lstm-model http://ceur-ws.org/Vol-2563/aics_41.pdfhttps://www.kaggle.com/datasets/borismarjanovic/price-volume-data-for-all-us-stocks-etfshttps://blog.quantinsti.com/machine-learning-logistic-regression-python/