Predicting Expected Profit in Ongoing Peer-to-Peer Loans with Survival Analysis-Based Profit Scoring

Abstract

The growing popularity of P2P lending has attracted more borrowers and lenders to the sector. With the growth in the popularity of P2P lending there have been many studies focusing on analyzing credit risk in P2P lending. However, the credit risk is only a part of the story. The higher interest rates are allocated to the riskier loans, and the higher interest rates may or may not in fact compensate for the defaults expected. Therefore, the profit of a loan depends on both the interest rate and the default probability. Since investors are ultimately concerned with return on investment, models should help investors to predict the profit as accurately as possible. We develop a model that predicts the expected profit of a loan using survival analysis based monthly default probability. Our approach extends previous profit scoring approaches, since it can be applied to any loan data set, including current data sets with many on-going loans.

Applying hybrid machine learning algorithms to assess customer risk-adjusted revenue in the financial industry

“…For instance, the highest 𝑅 2 is reached for the hybrid models clustering customers using k-Means++ and GB (95.3%). Byanjankar and Viljanen (2020) have shown that an improvement in forecasting the probability of default in the P2P settings results in a significant maximization of profits. Their study proposes a profitpredictive framework in the P2P industry.…”

Penentuan Harga Jual: Harga Pokok Produksi dan Ekspektasi Laba

“…Liverpool-Tasie, (2017); Nojavan et al, (2017), penelitiannya menyelidiki konsistensi upaya mencapai laba yang diharapkan secara maksimal. Sementara Byanjankar & Viljanen (2020), menyelidiki dan memprediksi keuntungan atas kembalilan investasi dengan mempertimbangkan berbagai risiko dari aktivitas bisnis sebagai objek yang ditelitinya. Penelitian yang menyelidiki upaya mencapai keuntungan maksimum yang diharapkan dengan menggunakan metode trade off waktu-biaya dilakukan Alavipour & Arditi (2019), dan penelitian yang berfokus pada upaya memaksimalkan ROI digunakan untuk menentukan kebijakan harga yang optimal (misalnya, Kevork, 2010;Abbas & Zellner, 2018;dan Pando et al, (2021).…”

“…Hal ini sejalan dengan beberapa temuan penelitian terdahulu, bahwa HPP merupakan unsur utama dalam penentuan harga jual, faktor eksternal di luar kendali termasuk ketatnya persaingan turut diperhitungkan sebagai risiko bisnis, sekaligus masuk dalam pertimbangan tinggi rendahnya persentase ROI sehingga mempengaruhi keputusan penentuan harga jual (Lu et al, 2017;Schönsleben, 2023;Noviasari & Alamsyah, 2020;Purwanto, 2020;dan Hasyim, 2019). Perlu dilakukan agar harga jual dapat menutupi semua biaya penuh, guna mengurangi ketidakpastian dan terhindar dari risiko kerugian (misalnya, Xu & Li, 2010;dan Wu et al, 2006;Paesbrugghe et al, 2022;dan Abdi, 2021), sehingga penentuan harga jual tidak terlalu tinggi/rendah dan kompetitif dengan harga jual kompetitor terutama produk sejenis (Hu & Su, 2018), biaya rendah menjamin konsistensi pencapaian keuntungan (Santos et al, 2016;Moheb-Alizadeh & Handfield, 2018;Liverpool-Tasie, 2017), akhirnya dihasilkan keputusan penentuan harga jual yang tepat (Dey et al, 2019;Thépot & Netzer, 2008;Goestjahjanti & Widayati, 2020;Ghoshal et al, 2021;Wu et al, 2022), di mana ini nantinya akan membantu manajemen dalam memprediksikan pencapaian laba seakurat mungkin (Byanjankar & Viljanen, 2020;dan Hu & Su, 2018).…”

Data‐driven optimization of peer‐to‐peer lending portfolios based on the expected value framework

“…In addition to risk prediction, few studies have implemented profit‐scoring approaches that predict the expected profit of a P2P loan (Byanjankar & Viljanen, 2019; Serrano‐Cinca & Gutiérrez‐Nieto, 2016). However, these approaches either isolate the risk and return or evaluate the risk and return only for a single loan at a time.…”