Full Description
| Cataloguing Source | LibUI ind rda |
| Content Type | text (rdacontent) |
| Media Type | computer (rdamedia) |
| Carrier Type | online resource (rdacarrier) |
| Physical Description | xv, 60 pages : illustration ; 28 cm |
| Concise Text | |
| Holding Institution | Universitas Indonesia |
| Location | Perpustakaan Lantai 3 |
- Availability
- Digital Files: 1
- Review
- Cover
- Abstract
| Call Number | Barcode Number | Availability |
|---|---|---|
| S-pdf | 14-22-87573078 | TERSEDIA |
| No review available for this collection: 20504848 |
Abstract
Laporan keuangan merupakan dokumen sangat penting yang menjadi basis dari keputusan berbagai stakeholder pada pasar modal. Ironisnya, fenomena fraud (kecurangan) pada laporan keuangan perusahaan bukan merupakan praktik yang tidak pernah terjadi. Data yang dilansir ACFE Chapter Indonesia pada tahun 2016 menunjukkan bahwa sekitar 40% dari kecurangan pada laporan keuangan menyebabkan kerugian yang mencapai lebih dari Rp. 10 milyar. Menurut laporanyang dirilis oleh ACFE pada tahun 2014, rata-rata waktu yang dibutuhkan untuk
mendeteksi kecurangan pada laporan keuangan adalah 24 bulan dengan total kerugian yang bisa mencapai US$ 150.000. Penelitian ini akan menggunakan pendekatan machine learning berbasis optimasi meta-heuristic untuk mengembangkan model prediksi fraud pada laporan keuangan. Terdapat beberapa metode klasifikasi yang dapat digunakan yaitu Neural Networks dan Support Vector Machine. Hasil prediksi terbaik pada penelitian ini berupa model Support Vector Machine dengan parameter teroptimasi dengan Genetic Algorithm yang mendapatkan akurasi sebesar 96.15%.
Financial statement is a critical document which form the basis of decisions of various stakeholders in the capital market. Ironically, the phenomenon of fraud (fraud) on the company's financial statements is not a practice that never happened. Data reported by ACFE Chapter Indonesia in 2016 showed that around 40% of the financial statement caused losses that reached more than Rp 10 billion. According to a report released by ACFE in 2014, the average time needed to detect fraud on financial statements is 24 months, with a total loss that could reach US$ 150,000. This study will use several machine learning approaches based on meta-heuristic optimization to develop fraud prediction models in financial statements. Two classification methods were utilized, namely, Back Propagation Neural Networks and Support Vector Machines. The best classifier in this study is a Support Vector Machine, which parameters are optimized with Genetic Algorithm resulting in 96.15% accuracy.
Financial statement is a critical document which form the basis of decisions of various stakeholders in the capital market. Ironically, the phenomenon of fraud (fraud) on the company's financial statements is not a practice that never happened. Data reported by ACFE Chapter Indonesia in 2016 showed that around 40% of the financial statement caused losses that reached more than Rp 10 billion. According to a report released by ACFE in 2014, the average time needed to detect fraud on financial statements is 24 months, with a total loss that could reach US$ 150,000. This study will use several machine learning approaches based on meta-heuristic optimization to develop fraud prediction models in financial statements. Two classification methods were utilized, namely, Back Propagation Neural Networks and Support Vector Machines. The best classifier in this study is a Support Vector Machine, which parameters are optimized with Genetic Algorithm resulting in 96.15% accuracy.