Publication Search

This study proposes the integration of a Hybrid Recommendation method (combining Content-Based and Collaborative Filtering) with Random Forest Regression (RFR) to improve the accuracy of stay duration prediction in web-based boarding house booking systems. The main issue in online boarding booking systems is the inaccuracy of predicting user stay duration, affecting room allocation efficiency and customer satisfaction. The dataset was sourced from the hotel sector due to its attribute similarities and data validity. The research process includes data preprocessing (missing value imputation, normalization, and one-hot encoding), temporal and contextual feature engineering, hybrid recommendation system construction with CBF and CF score weighting, and RFR model training optimized through Grid Search and 10-fold cross-validation. Evaluation was conducted using MAE, RMSE, R² metrics, as well as recommendation metrics such as Precision@5, Recall@5, and Mean Reciprocal Rank (MRR). Results show that this integrated model achieved an R² of 0.7239 and an MAE of 1.0537 days, as well as a Precision@5 of 0.9636. This integration proves effective in improving prediction accuracy and recommendation relevance and contributes to the development of AI-based intelligent systems in the accommodation domain.

Tourism plays an important role in the economic growth of Bengkalis District, but limited access to hotel and lodging information poses challenges for travelers. This study develops a mobile application to simplify accommodation searches with a feature that finds the nearest route using the A* algorithm. The algorithm calculates the optimal route based on selected transportation options, such as walking, motorbike, or car, making travel more efficient. Testing results show that the A* algorithm provides more accurate routes compared to conventional methods, with an average response time of 4.9 seconds and 95% accuracy, compared to Google Maps, which has a response time of 6.2 seconds and 90% accuracy. This app also provides information about hotel facilities, prices, and contact details, helping travelers choose accommodations. With this application, travelers can quickly find accommodations, while hotel managers gain increased visibility. This research supports Bengkalis' tourism sector with a technology-based solution that facilitates information access and trip planning. Future updates may include booking and payment features to enhance the app's functionality.

This study aims to analyse the increase in Harper Hotel revenue to Medan City's local revenue. There is a dependent variable, namely the Regional Original Revenue of Medan City, and two independent variables, namely lodging and other hotel revenue. This research uses primary data by conducting direct data searches on the management of Harper Hotel. The data analysis model in this study uses multiple linear regression. The results showed that the Lodging Revenue and Other Revenue Variables had a significant effect on Regional Original Revenue in Medan City.