MODEL PREDIKSI FINANCIAL DISTRESS MENGGUNAKAN ARTIFICIAL NEURAL NETWORK

• Main Author: Ayesha Nur Sakinah, - (Author)
• Format: Book
• Published: 2019-04-24.
• Subjects: Thesis; NonPeerReviewed
• Online Access: Link Metadata
• Notes: http://repository.upi.edu/34737/1/S_PEA_1403388_Title.pdf; http://repository.upi.edu/34737/2/S_PEA_1403388_Chapter1.pdf; http://repository.upi.edu/34737/3/S_PEA_1403388_Chapter2.pdf; http://repository.upi.edu/34737/4/S_PEA_1403388_Chapter3.pdf; http://repository.upi.edu/34737/5/S_PEA_1403388_Chapter4.pdf; http://repository.upi.edu/34737/6/S_PEA_1403388_Chapter5.pdf; http://repository.upi.edu/34737/7/S_PEA_1403388_Appendix.pdf
• Keywords: HF5601 Accounting; L Education (General)

Penelitian ini bertujuan untuk mengetahui model prediksi financial distress menggunakan artificial neural network (ANN). Sampel pada penelitian ini menggunakan teknik purposive sampling, dengan jumlah sampel sebanyak 20 BUMN. Data sekunder dikumpulkan dari laporan keuangan BUMN periode 2013 - 2017 yang diperoleh dari website setiap perusahaan BUMN. Jenis penelitian ini adalah penelitian deksriptif dengan pendekatan kuantitatif. Alat analisis yang digunakan adalah teknik analisis artificial neural network (ANN). Input dalam penelitian ini menggunakan kinerja keuangan, diproksikan dengan Rasio Profitabilitas, Rasio Solvabilitas dan Rasio Likuiditas. Hasil penelitian menunjukkan bahwa, Rasio Profitabilitas, Rasio Solvabilitas dan Rasio Likuiditas dapat digunakan untuk membentuk model prediksi financial distress. Model prediksi financial distress dapat digunakan sebagai early warning system (EWS) bagi BUMN untuk mengantisipasi kebangkrutan. This research aims to determine financial distress prediction model using artificial neural network (ANN). The sample is determined by purposive sampling techniques, thus predetermined number of sample are 20 BUMN. Secondary data were collected from BUMN's Financial Report in 2013-2017 taken from each of BUMN's website. Type of this research is decriptive quantitative approach. Technique of analysis is artificial neural network (ANN). Input in this research are financial performance used profitability ratio, solvability ratio and liquidity ratio as proxy. This study showed profitability ratio, solvability ratio and liquidity ratio can be used to construct financial distress prediction model. This financial distress prediction model can be used as early warning system (EWS) for BUMN to prevent bankruptcy.