{"id":21239194,"url":"https://github.com/cutupdev/deep-learning-for-oil-price-forecasting-using-multivariate","last_synced_at":"2026-05-21T04:05:02.508Z","repository":{"id":223128288,"uuid":"759373806","full_name":"cutupdev/Deep-Learning-for-Oil-Price-Forecasting-using-Multivariate","owner":"cutupdev","description":"This is oil price forecasting project using LSTM and GRU.","archived":false,"fork":false,"pushed_at":"2024-02-18T13:10:48.000Z","size":7090,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-15T03:41:12.233Z","etag":null,"topics":["gru","jupyter-notebook","lstm","prediction","python"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cutupdev.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2024-02-18T12:20:24.000Z","updated_at":"2025-03-07T16:04:55.000Z","dependencies_parsed_at":"2024-02-21T09:37:02.908Z","dependency_job_id":null,"html_url":"https://github.com/cutupdev/Deep-Learning-for-Oil-Price-Forecasting-using-Multivariate","commit_stats":null,"previous_names":["catlover75926/deep-learning-for-oil-price-forecasting-using-multivariate","harmonitech/deep-learning-for-oil-price-forecasting-using-multivariate","cutupdev/deep-learning-for-oil-price-forecasting-using-multivariate"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/cutupdev/Deep-Learning-for-Oil-Price-Forecasting-using-Multivariate","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cutupdev%2FDeep-Learning-for-Oil-Price-Forecasting-using-Multivariate","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cutupdev%2FDeep-Learning-for-Oil-Price-Forecasting-using-Multivariate/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cutupdev%2FDeep-Learning-for-Oil-Price-Forecasting-using-Multivariate/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cutupdev%2FDeep-Learning-for-Oil-Price-Forecasting-using-Multivariate/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cutupdev","download_url":"https://codeload.github.com/cutupdev/Deep-Learning-for-Oil-Price-Forecasting-using-Multivariate/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cutupdev%2FDeep-Learning-for-Oil-Price-Forecasting-using-Multivariate/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33288158,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-21T02:57:32.698Z","status":"ssl_error","status_checked_at":"2026-05-21T02:57:31.990Z","response_time":62,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["gru","jupyter-notebook","lstm","prediction","python"],"created_at":"2024-11-21T00:42:23.970Z","updated_at":"2026-05-21T04:05:02.493Z","avatar_url":"https://github.com/cutupdev.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Multivariate Analysis-Oil Price Prediction Using LSTM \u0026 GRU\n![My Image](multivariate.JPG)\n\n\n## Project Overview \nWe carry out Analysis between variables like **West Texas intermediate(WTI), Gold Futures , US Dollar Index Futures, US 10 Year Bond Yield,Gold Futures, S\u0026P 500, Dow Jones Utility Average**. \nExperiment out different **outliers techniques** like (1)**Zscore**, (2)**Removing Financial Crisis** Period (2007-2009 recession period) and (3)**Mahalanobis Distance** .\nWe then carry out comparision by observing **forecasting differences** across two models **Long Term Short Memory(LSTM) and Gated Re-current Unit(GRU)**.\n\n## Motivation\nEarlier I had worked on a time series prediction problem dealing with Apple Stock Price prediction using Seasonal-ARIMA \u0026 Prophet. \nI had an univariate series to deal with. Later when I dived into other methods for forecasting time series problems, I came across Deep Neural Network Techniques like LSTM and GRU. Also,came across using multiple explanatory variables to account for many effects to account for economic changes, etc.\nOil seemed interesting to me after I came across it in my economic course.\nIt was a interesting project to forecast oil price and observe relationship wrt to some economic variables like Gold Futures,Interest rates and Market Indices, etc.\n\n\n## Problem Type\nLSTM and GRU for Time Series Forecasting Problem using Multivariant.\n\n**Result Metrics**\n\nMean Squared Error(MSE),Mean Absolute Error(MAE), R2 Score.\n\n## Actionable Insight\nUnderstanding behaviour of Oil price and whether to invest it in or not.\n\n## Tools \u0026 Libraries Used\n- **Python 3.6**\n- **Pandas**        \n- **Matplotlib**        \n- **Sklearn**            \n- **Seaborn**\n- **Statsmodels**      \n- **Scipy** \n- **Keras with Tensorflow Backend**\n- **Plotly** \n\n\n\n       \n\n## About the Data\nIndividual Data series was collected from Investing.com site (https://www.investing.com/) and Yahoo Finance (https://finance.yahoo.com/). \nTime period for data ranges between 4th Jan 2000 to 10th June 2019 with Daily frequency containing 4947 records in total and 7 series in total.\nThe following series -(WTI ,Gold Futures , US Dollar Index Futures, US 10 Year Bond Yield,Gold Futures, S\u0026P 500, )-Investing.com and (Dow Jones Utility Average)-Yahoo Finance.\n\n## Initial Preprocessing \nTo work on the dataset similar to the project, the following steps were carried out .\n\n-\u003e We collect individual time series within the same range for each feature.\n\n-\u003e Using VlookUp from Excel we merge the series into one dataset , we do so by the dates to align it according to the target variable WTI.\n\n***Note***: We have put both individual time series and combined dataset in the data folder of this repo..\n\n\n## Credits/Resources\n-https://www.investing.com/\n\n-https://finance.yahoo.com/\n\n-https://towardsdatascience.com/illustrated-guide-to-lstms-and-gru-s-a-step-by-step-explanation-44e9eb85bf21\n\n-https://machinelearningmastery.com/multivariate-time-series-forecasting-lstms-keras/\n\n-https://machinelearningmastery.com/how-to-develop-lstm-models-for-time-series-forecasting/\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcutupdev%2Fdeep-learning-for-oil-price-forecasting-using-multivariate","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcutupdev%2Fdeep-learning-for-oil-price-forecasting-using-multivariate","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcutupdev%2Fdeep-learning-for-oil-price-forecasting-using-multivariate/lists"}