Hasil pencarian

ThesisOpen AccessMetadata saja

DETEKSI FINANCIAL STATEMENT FRAUD MENGGUNAKAN RANDOM FOREST PADA PERUSAHAAN MANUFAKTUR YANG TERDAFTAR DI BURSA EFEK INDONESIA (BEI)

TARISAH

2026•Skripsi, Thesis, Disertasi, dan Tugas Akhir

Kecurangan laporan keuangan (Financial Statement Fraud) merupakan masalah serius yang dapat merugikan investor dan pengguna laporan keuangan. Seiring perkembangan teknologi, metode konvensional dinilai belum optimal sehingga diperlukan pendekatan Machine Learning. Penelitian ini bertujuan untuk mengetahui kemampuan Random Forest dalam mendeteksi Financial Statement Fraud serta mengidentifikasi variabel yang paling berkontribusi berdasarkan Fraud Triangle. Penelitian ini menggunakan pendekatan kuantitatif pada perusahaan manufaktur yang terdaftar di Bursa Efek Indonesia (BEI) periode 2021–2024. Sampel penelitian terdiri atas 73 perusahaan dengan 292 observasi yang dipilih menggunakan teknik purposive sampling. Deteksi fraud dilakukan menggunakan Beneish M-Score dengan variabel Financial Target, External Pressure, Nature of Industry, dan Change in Auditor. Data diolah melalui pre-processing, SMOTE, dan pemodelan Random Forest. Hasil penelitian menunjukkan bahwa Random Forest mampu mendeteksi fraud dengan nilai accuracy sebesar 0,7627. Variabel yang paling dominan adalah Nature of Industry, diikuti Financial Target dan External Pressure, sedangkan Change in Auditor memiliki kontribusi paling kecil. Kesimpulannya, Random Forest dapat digunakan sebagai metode dalam mendeteksi Financial Statement Fraud, meskipun masih perlu pengembangan lebih lanjut. Financial statement fraud is a serious issue that can harm investors and users of financial statements. By advancement of technology, conventional methods are considered suboptimal, necessitating a Machine Learning approach. This study aims to determine the ability of Random Forest to detect financial statement fraud and to identify the variables that contribute most significantly based on the Fraud Triangle. This study employed a quantitative approach on manufacturing companies listed on the Indonesia Stock Exchange (IDX) for the period 2021–2024. The research sample consisted of 73 companies with 292 observations selected using purposive sampling. Fraud detection was performed using the Beneish M-Score with the variables Financial Target, External Pressure, Nature of Industry, and Change in Auditor. The data was processed through pre-processing, SMOTE, and Random Forest modeling. The results showed that Random Forest is capable of detecting fraud with an accuracy of 0.7627. The most dominant variable is Nature of Industry, followed by Financial Target and External Pressure, while Change in Auditor has the smallest contribution. In conclusion, Random Forest can be used as a method for detecting Financial Statement Fraud, although further development is still needed.

Kata Kunci: Beneish M-ScoreFinansial Statement FraudFraud TriangleMachine LearningRandom Forest Keywords: Beneish M-ScoreFinancial Statement FraudFraud TriangleMachine LearningRandom Forest

0 dilihat · 0 unduhanSitasiDetail

ThesisOpen AccessMetadata saja

Kinerja Machine Learning dalam memprediksi kecurangan laporan keuangan berdasarkan Teori Fraud Pentagon pada perusahaan Consumer Cyclical

RITA

2026•

Penelitian ini bertujuan menganalisis kinerja machine learning dalam memprediksi kecurangan laporan keuangan berdasarkan teori fraud pentagon serta mengidentifikasi kontribusi masing-masing variabel fraud pentagon. Penelitian menggunakan pendekatan kuantitatif dengan 385 observasi perusahaan sektor consumer cyclical yang terdaftar di Bursa Efek Indonesia periode 2020–2024. Kecurangan laporan keuangan diukur menggunakan Beneish M-Score, sedangkan variabel independen meliputi pressure, opportunity, rationalization, capability, dan arrogance. Analisis dilakukan menggunakan random forest sebagai model utama, dengan logistic regression dan Ordinary Least Squares (OLS) sebagai model pembanding serta SMOTE untuk menangani ketidakseimbangan data. Hasil penelitian menunjukkan bahwa model machine learning memiliki kinerja lebih baik dibandingkan OLS, dengan logistic regression menghasilkan performa terbaik dan random forest menunjukkan kemampuan prediksi yang sangat tinggi. Analisis feature importance menunjukkan bahwa pressure merupakan variabel yang paling dominan, diikuti oleh opportunity, arrogance, capability, dan rationalization. Temuan ini mengindikasikan bahwa tekanan untuk mencapai target kinerja keuangan menjadi faktor utama yang berkontribusi terhadap risiko kecurangan laporan keuangan pada perusahaan sektor consumer cyclical.

Feature ImportanceFraud PentagonMachine LearningRandom Forest

0 dilihat · 0 unduhanSitasiDetail

ThesisOpen AccessMetadata saja

Pemanfaatan Machine Learning untuk Deteksi Kecurangan Laporan Keuangan : Sintesis Literatur

AGNESIA PEBRIANA IRA LONG

2026•Skripsi, Thesis, Disertasi, dan Tugas Akhir

Artificial intelligence advancements are transforming accounting and auditing methods, particularly in identifying fraud in increasingly complicated financial accounts The limitations of conventional audit methods in identifying patterns of anomalies in large-scale data have led to the use of machine learning as a more efficient approach. This study was to investigate global research trends, identify the methods employed, and suggest future research prospects. The method used was a systematic literature review (SLR) based on PRISMA criteria, with 162 publications picked from the Scopus database between 2019 and 2024 The results show a huge rise in research. Decision trees, support vector machines, and neural networks are the most commonly utilized algorithms for categorizing fraud and non-fraud data. Although effective, the method is limited in terms of interpretability and data requirements. This study provides an overview of the current state of the art and lays the groundwork for future technology-based audit research and practice.

Machine learningfinancial statement fraudfraud detectionsystematic literature review

0 dilihat · 0 unduhanSitasiDetail