Claim Missing Document
Check
Articles

Found 2 Documents
Search

Predicting Hotel Booking Cancellations Using CatBoost and SHAP: An Explainable AI Approach Based on 2020–2026 Operational Data I Made Sudana; Endang Wahyu Pamungkas
Computer Journal Vol. 4 No. 2 (2026): August
Publisher : Yayasan Pendidikan Mitra Mandiri Aceh (YPMMA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58477/cj.v4i2.511

Abstract

Hotel booking cancellations are a critical problem in hotel revenue management because they can cause operational inefficiencies and financial losses. This study develops an explainable cancellation prediction model using CatBoost integrated with SHAP, based on real-world Property Management System (PMS) operational data from a budget hotel in Central Java, Indonesia. The dataset spans 67 months (October 2020–April 2026) and, after preprocessing and data cleaning, yields 74,826 independent reservation records from 80,110 raw entries. The cancellation rate is extremely low (1.56%), creating a severe class imbalance challenge. Instead of synthetic oversampling, the proposed method applies cost-sensitive learning via CatBoost’s scale_pos_weight, computed from the natural class ratio. Model performance is evaluated using hold-out validation (80% training, 20% testing). The proposed CatBoost model achieves an F1-score of 72.04%, with precision of 87.20% for the cancellation class and an AUC-ROC of 0.86, outperforming Random Forest and XGBoost baselines. SHAP analysis indicates that lead time, deposit type, and arrival month are the most influential features driving cancellation predictions. These findings support early warning decision-making for risk mitigation in hotel operations.
Hybrid Cybersecurity Compliance Audit Framework for an On-Premise Hotel Property Management System: Mapping NIST CSF 2.0 Controls to Indonesia's Personal Data Protection Law I Made Sudana; Bana Handaga; Jan Wantoro
Jurnal Sistem Informasi Vol. 22 No. 2 (2026): Jurnal Sistem Informasi (Journal of Information System)
Publisher : Faculty of Computer Science Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jsi.v22i2.1612

Abstract

The accelerating digitalization of Property Management Systems (PMS) in the hospitality sector introduces substantial cybersecurity exposure, particularly concerning the protection of guests' personal data. This study audits the cybersecurity posture of an on-premise e-VHP PMS operated by an international chain hotel in Surakarta, Indonesia, whose local PMS core is integrated with cloud-based third-party Channel Manager and Online Travel Agency (OTA) platforms managed at the corporate level. A hybrid audit instrument was developed to bridge technical controls under NIST Cybersecurity Framework (CSF) 2.0 with legal obligations under Indonesia's Personal Data Protection Law (UU PDP) No. 27/2022. Primary data were collected through structured interviews with six informants representing three organizational layers: managerial (General Manager), technical (two IT Officers), and operational/front-line staff (Front Office, General Cashier/Accounts Payable, and Income Audit/Accounts Receivable), using a five-point maturity rubric (1 = Not Implemented to 5 = Optimized and Continuously Reviewed). Aggregated maturity scores showed that Detect (3.33) and Govern (3.00) achieved the highest relative maturity, whereas Respond (1.50) and Recover (1.89) showed the most severe capability deficits; Protect (2.50) and Identify (2.44) fell in between. Gap analysis against the optimal target (5.00) placed Respond at the highest remediation priority (Gap = 3.50), followed by Recover (Gap = 3.11). A cost-sensitive risk register identified critical exposure in endpoint backup failure and unmanaged credential sharing among front-line staff, alongside high power-management and integration-channel risks. Structural mapping shows these technical and behavioral gaps correspond to potential non-compliance with Articles 35, 39, and 46 of the UU PDP, exposing the organization to administrative fines of up to 2% of annual revenue. The study proposes a tiered Cybersecurity Governance Blueprint emphasizing local incident-response capability, standardized power-backup procurement, encrypted endpoint backup automation, and a structured security-awareness program for front-line personnel.