{"id":20608917,"url":"https://github.com/jose-jaen/airbnb","last_synced_at":"2025-04-15T04:25:05.956Z","repository":{"id":62708252,"uuid":"550929607","full_name":"jose-jaen/Airbnb","owner":"jose-jaen","description":"Airbnb price prediction using Machine Learning and Deep Learning","archived":false,"fork":false,"pushed_at":"2023-05-28T14:59:45.000Z","size":26918,"stargazers_count":13,"open_issues_count":1,"forks_count":4,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-28T15:51:50.185Z","etag":null,"topics":["ai","algorithms","bayes","bayesian-optimization","bayesian-statistics","data-science","deep-learning","deployment","econometrics","machine-learning","python","streamlit","xai"],"latest_commit_sha":null,"homepage":"","language":"Python","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/jose-jaen.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,"publiccode":null,"codemeta":null}},"created_at":"2022-10-13T14:55:56.000Z","updated_at":"2025-02-15T14:45:39.000Z","dependencies_parsed_at":"2024-11-16T11:04:23.413Z","dependency_job_id":null,"html_url":"https://github.com/jose-jaen/Airbnb","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jose-jaen%2FAirbnb","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jose-jaen%2FAirbnb/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jose-jaen%2FAirbnb/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jose-jaen%2FAirbnb/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jose-jaen","download_url":"https://codeload.github.com/jose-jaen/Airbnb/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249005057,"owners_count":21197010,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["ai","algorithms","bayes","bayesian-optimization","bayesian-statistics","data-science","deep-learning","deployment","econometrics","machine-learning","python","streamlit","xai"],"created_at":"2024-11-16T10:12:14.792Z","updated_at":"2025-04-15T04:25:05.919Z","avatar_url":"https://github.com/jose-jaen.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Airbnb Price Prediction :house:\n\nLooking for a fair-priced Airbnb listing to book? \n\nAre you a real estate firm or Airbnb host seeking to set competitive prices?\n\nArtificial Intelligence is surely the way to go! :robot:\n\nIn this Quantitative Economics Bachelor Thesis, Machine Learning and Deep Learning algorithms are used to accurately predict Airbnb rental prices.\n\nTwo datasets for Los Angeles city are retrieved from [Inside Airbnb](http://insideairbnb.com/): listings data and the reviews dataset.\n\nCombining custom functions, transfer learning and Open Source AI frameworks such as scikit-learn, TensorFlow and PyTorch, several AI models are built to help economic agents make informed decisions.\n\nA Bayesian perspective is taken to perform statistical inference, hyperparameter tuning and data modeling.\n\nAdditionally, XAI methods are used to overcome the black box problem of AI algorithms.\n\n# Price Prediction App\n[![Streamlit App](https://static.streamlit.io/badges/streamlit_badge_black_white.svg)](https://airbnb-prices.streamlit.app/)\n\nClick on the icon above to acces the Airbnb Price Prediction Web App!\n\n# Bachelor Thesis Document\n\nThe link below gives access to the thesis explaining all Machine Learning, XAI and Statistical Inference techniques. \n\n- [Thesis Document](https://github.com/jose-jaen/Airbnb/blob/main/Project/Thesis.pdf)\n\n# General Code\n\nSince Python code has been divided into multiples files, the one below combined all the programmed functions for retrieving relevant results.\n\n- [Project Code](https://github.com/jose-jaen/Airbnb/blob/main/Project/airbnb_project.py)\n\n# Preprocessing and Responsible AI\n\nFrom creating and modifying features to opening the black box problem of AI, all Data Mining algorithms can be found in the following link.\n\n- [Data Cleaning, Feature Engineering \u0026 XAI](https://github.com/jose-jaen/Airbnb/blob/main/Functions/general_functions.py)\n\n# NLP and CV\n\nNLP and Computer Vision algorithms used on the reviews and listings dataset, respectively. \n\nVADER, a sentiment analysis tool was tweaked so as to adapt it to Airbnb data.\n\nFor CV, a pretrained Deep Learning model called deepface was utilized.\n\n- [NLP algorithms](https://github.com/jose-jaen/Airbnb/blob/main/Functions/nlp_functions.py)\n\n- [Computer Vision algorithms](https://github.com/jose-jaen/Airbnb/blob/main/Functions/cv_functions.py)\n\n# Machine Learning and Deep Learning\n\nAI algorithms for predicting prices. In the ML part, Bayesian Ridge Regression, Elastic Net Regression, Random Forest, Bayesian Random Forest,\nand XGBoost were used.\n\nFor DL, Artificial Neural Networks and Bayesian Neural Networks were built. \n\nNote that TPE algorithm (Bayesian Optimization) was used to select the best performing hyperparameters.\n\n- [Machine Learning modeling](https://github.com/jose-jaen/Airbnb/blob/main/Functions/ml_models.py)\n\n- [Deep Learning modeling](https://github.com/jose-jaen/Airbnb/blob/main/Functions/dl_models.py)\n\n- [Bayesian Random Forest adaption](https://github.com/jose-jaen/Airbnb/blob/main/Functions/_forest.py)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjose-jaen%2Fairbnb","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjose-jaen%2Fairbnb","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjose-jaen%2Fairbnb/lists"}