{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T05:46:31Z","timestamp":1773380791986,"version":"3.50.1"},"reference-count":0,"publisher":"Slovenian Association Informatika","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJCAI"],"abstract":"<jats:p>Energy management in residential buildings has become an important issue in today's time, as it accounts for a huge amount of energy consumption globally. In residential buildings, an appropriate prediction of energy use helps in promoting energy conservation and aids informed decision-making on issues that can help reduce consumption. Architectural design and building form are very relevant to the growth of energy consumption, mostly in residential areas. The present work is going to develop a model for predicting energy consumption for different types of residential buildings with the help of machine learning methods. In this paper, the SVR and CatBoost algorithms are combined with the HGS method for tuning and optimizing their hyperparameters to improve the accuracy of the predictions. The dataset used in this study comprises over a million records of Irish residential buildings, including terraced houses (type 1), detached houses (type 2), bungalows (type 3), and semi-detached houses (type 4), with 18 input features and two output variables: \"Interior Lighting Energy\" and \"Total Heating Energy.\" The performance of both models is evaluated using numerical metrics, including MAE and MAPE for each energy variable. It provides insight that the SVR-HGS hybrid model was best at forecasting interior lighting energy with an MAE of 1.6761 and MAPE of 0.0029, and the CatBoost-HGS hybrid model gave the most accurate forecast of total heating energy with an MAE of 1817.8 and MAPE of 0.3587 in the buildings under examination.<\/jats:p>","DOI":"10.31449\/inf.v50i9.7735","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T22:21:31Z","timestamp":1773354091000},"source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Machine Learning Models for Predicting Energy Consumption in Residential Building Types Using Architectural Features"],"prefix":"10.31449","volume":"50","author":[{"given":"Xueli","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziru","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"16141","published-online":{"date-parts":[[2026,3,12]]},"container-title":["Informatica"],"original-title":[],"link":[{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/download\/7735\/6568","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/download\/7735\/6568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T22:21:31Z","timestamp":1773354091000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/view\/7735"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,12]]},"references-count":0,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,3,12]]}},"URL":"https:\/\/doi.org\/10.31449\/inf.v50i9.7735","relation":{},"ISSN":["1854-3871","0350-5596"],"issn-type":[{"value":"1854-3871","type":"electronic"},{"value":"0350-5596","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,12]]}}}