Treffer: Integrasi Analytic Hierarchy Process (AHP)–Machine Learning yang Dinamis dalam Prediksi Risiko Kredit.

In recent years, credit risk in the MSME sector has increased sharply due to the limitations of traditional valuation models that tend to ignore the complexity of data and expert preferences. To answer these challenges, this study proposes the integration of Analytical Hierarchy Process (AHP) and Machine Learning (ML) algorithms, especially Random Forest, as a hybrid approach in credit risk prediction. This research aims to develop an accurate and explainable predictive system, by combining the power of AHP as an expert weighting tool and ML as a data-based classification engine. The research methodology involves normalization of MSME datasets, training of Random Forest models using WEKA and Python, and integration of AHP weights into the classification threshold calibration process. Interviews with credit experts are used to form an AHP comparison matrix and ensure weight consistency. The results showed that the initial Random Forest model had an accuracy of 89.5% and an AUC of 96.6%. After the integration of AHP, precision increased to 100%, although the recall decreased to 82.8%, signaling a shift to a conservative strategy. The empirically optimal threshold was achieved at 0.583 with an F1 score of 91.89%. In conclusion, AHP–ML integration not only improves model performance statistically, but also strengthens transparency and decision-making flexibility, making it an ideal solution for risk management and adaptive credit policies in the financial sector. [ABSTRACT FROM AUTHOR]

Dalam beberapa tahun terakhir, risiko kredit pada sektor UMKM meningkat tajam akibat keterbatasan model penilaian tradisional yang cenderung mengabaikan kompleksitas data dan preferensi pakar. Untuk menjawab tantangan tersebut, penelitian ini mengusulkan integrasi metode Analytical Hierarchy Process (AHP) dan algoritma Machine Learning (ML), khususnya Random Forest, sebagai pendekatan hybrid dalam prediksi risiko kredit. Penelitian ini bertujuan mengembangkan sistem prediktif yang akurat dan dapat dijelaskan, dengan menggabungkan kekuatan AHP sebagai alat pembobotan pakar dan ML sebagai mesin klasifikasi berbasis data. Metodologi penelitian melibatkan normalisasi dataset UMKM, pelatihan model Random Forest menggunakan WEKA dan Python, serta integrasi bobot AHP ke dalam proses kalibrasi threshold klasifikasi. Wawancara dengan pakar kredit digunakan untuk membentuk matriks perbandingan AHP dan memastikan konsistensi bobot. Hasil menunjukkan bahwa model Random Forest awal memiliki akurasi 89,5% dan AUC 96,6%. Setelah integrasi AHP, precision meningkat menjadi 100%, meskipun recall menurun menjadi 82,8%, menandakan pergeseran ke strategi konservatif. Threshold optimal secara empiris tercapai di 0,583 dengan F1-score 91,89%. Kesimpulannya, integrasi AHP–ML tidak hanya meningkatkan performa model secara statistik, tetapi juga memperkuat transparansi dan fleksibilitas pengambilan keputusan, menjadikannya solusi ideal bagi manajemen risiko dan kebijakan kredit yang adaptif di sektor keuangan. [ABSTRACT FROM AUTHOR]

Copyright of Jurnal Locus: Penelitian dan Pengabdian is the property of Riviera Publishing and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)