Wholesale Gasoline Price Prediction

The goal of the project is to predict future wholesale gasoline prices obtained from a Polish oil company, LOTOS. The data is scraped from the website.

One model is bulit using an LSTM. Another one is ARIMA. The performance is compared in terms of mean squarred error and using plots.

Technology

• Python 3.10
• pipenv
• beautifulsoup4
• keras
• tensorflow

Resources

https://towardsdatascience.com/time-series-forecasting-predicting-stock-prices-using-an-arima-model-2e3b3080bd70

https://towardsdatascience.com/lstm-time-series-forecasting-predicting-stock-prices-using-an-lstm-model-6223e9644a2f