Prediction of Stock Prices using ARIMA Model in R Studio and generation of Variability Matrix to find the Dependency Relationship between Stocks
• Downloaded closing price data from year 2011 to 2021 of stocks from different sectors.
• Preprocessed the time series data and split it into training and testing datasets.
• Used ARIMA (AutoRegressive Integrated Moving Average) models to forecast the prices of stocks with a confidence interval of 95%.
• Used MAPE (Mean Absolute Percentage Error) to validate the performance of the model by comparing the predicted values to the test dataset. Used RMSE (Root Mean Square Error) to evaluate the best fit models.
• Normalized the data before implementing variability statistics using min-max scaling to mitigate the effect of outliers. Plotted covariance and correlation matrix for all stocks to analyze the dependencies between stocks.