Effect of Macroprudential Loan to Value (LTV) Policy using the Support Vector Regression (SVR) Approach

Siti Saadah, Muhammad Ridaffa Purnomo

Abstract


Macroprudential policy has a goal to confine the risk and price from crises systemic, especially in managing financial stability amidst the COVID-19 pandemic. One of its instruments is Loan to Value (LTV). Ratio of LTV is a ratio between value of credit or cost that can gave from Bank Conventional or Syariah towards collateral value as property. This study aims in getting to know about its influence on citizen to take Kredit Kepemilikan Rumah (KPR). Based on the data from Central Bank Indonesia (BI) would be found about the increasing ratio of LTV yoy. The data set in this study derived from five bank with the data range being from 2014 to 2020. According to the characteristic data that will be used, thus one of the algorithm machine learning that is Support Vector Regression (SVR) was chosen as an approach to observe this trend. By using this method, the result indicated which bank that had been influenced by LTV ratio. Category of the bank who got impact are the bank that had the reverse influence between credit value of home ownership, they are Foreign Bank, Mixed Bank, Bank Persero, Bank Swasta, and Bank Perkreditan Rakyat.

Keywords


Loan to Value (LTV); Macroprudential; Support Vector Regression (SVR); KPR.

Full Text:

PDF (Indonesian)

References


Abdelhamid, M. H., & Tawfik Elmasry, M. (2019). Machine Learning Approach for Credit Score Analysis: A Case Study of Predicting Mortgage Loan Defaults. Universidade Nova de Lisboa https://run.unl.pt/bitstream/10362/62427/4/TEGI0439.pdf

Anchal Goyal and Ranpreet Kaur, February 2016, Accuracy Prediction for Loan Risk Using Machine Learning Models. International Journal of Computer Science Trends and Technology (IJCST) – Volume 4 Issue 1.

Bank Indonesia. Rasio Loan to Value atau Financing to Value (LTV/FTV). Retrieved from Bank Indonesia: https://www.bi.go.id/id/ssk/Instrumen-Makroprudensial/LTV-FTV DP/Contents/default.aspx

Cortes, C., Vapnik, V. (1995). Support-vector networks. Mach Learn 20, 273–297. https://doi.org/10.1007/BF00994018

Douglas K et al, November 2017, Loan-to-value policy and housing finance: effects on constrained borrowers, Paper produced as part of the BIS Consultative Council for the Americas (CCA) research project. https://www.bis.org/publ/work673.pdf

Dushimimana, B., Wambui, Y., Lubega, T., & McSharry, P. E. (2020). Use of Machine Learning Techniques to Create a Credit Score Model for Airtime Loans. Journal of Risk and Financial Management, 13(8), 180. https://doi.org/10.3390/jrfm13080180

E. Chandra Blessie and R. Rekha, November 2019, Exploring the Machine Learning Algorithm for Prediction the Loan Sanctioning Process, International Journal of Innovative Technology and Exploring Engineering (IJITEE) ISSN: 2278-3075, Volume-9 Issue-1. https://doi.org/10.35940/ijitee.A4881.119119

Efrizoni, L. (2021). Prediction Model Grade Point Average using Backpropagation Neural Network and Multiple Linear Regression. Telematika, 14(1), 33–46. https://doi.org/10.35671/telematika. v14i1.1113

Ganstrom D and Abraham J, 2019, Loan Default Prediction using Supervised Machine Learning Algorithms, https://kth.diva-portal.org/smash/get/diva2:1319711/FULLTEXT02.pdf

Goyal, A., Kaur, R., & Research Scolar. (2013). Accuracy Prediction for Loan Risk Using Machine Learning Models. International Journal of Computer Science Trends and Technology, 4(1). Retrieved from www.ijcstjournal.org

de Araujo, D. K. G., Barroso, J. B. R. B., & Gonzalez, R. B. (2020). Loan-to-value policy and housing finance: Effects on constrained borrowers. In Journal of Financial Intermediation (Vol. 42, p. 100830). Elsevier BV. https://doi.org/10.1016/j.jfi.2019.100830

Lim, C., & Nugraheni, S. (2017). Loan-to-Value Ratio and Housing Price Cycle: Empirical Evidence From Indonesia. Jurnal Ekonomi Pembangunan: Kajian Masalah Ekonomi Dan Pembangunan, 18(2), 225. https://doi.org/10.23917/jep.v18i2.4846

Zhu, L., Qiu, D., Ergu, D., Ying, C., & Liu, K. (2019). A study on predicting loan default based on the random forest algorithm. In Procedia Computer Science (Vol. 162, pp. 503–513). Elsevier BV. https://doi.org/10.1016/j.procs.2019.12.017

Maharesi, R, (2013), Penggunaan Support Vector Regression (SVR) pada prediksi Return Saham Syariah BEI, Bandung: PESAT (Psikologi, Ekonomi, Sastra, Arsitektur & Teknik Sipil). https://core.ac.uk/download/pdf/231285662.pdf

Niu, B., Ren, J., & Li, X. (2019). Credit scoring using machine learning by combing social network information: Evidence from peer-to-peer lending. Information (Switzerland), 10(12). https://doi.org/10.3390/INFO10120397

Peter J. Morgan, Paulo José Regis, and Nimesh Salike, March 2015, Loan-to-Value Policy as a Macroprudential Tool: The Case of Residential Mortgage Loans in Asia, ADBI Working Paper 528.

Ramanjani R, September 2017, Machine Learning Classification: Prediction of Loan Approval, Machine Learning Classification: Prediction of Loan Approval – Rajivs geeky stuff (wordpress.com)

Sasikirono, N., Sumanto, S., Made Sudana, I., Meidiaswati, H., & Mandiri Sekuritas, P. (2019). 267-Loan-to-Value Policy and Property Loans Risk in Conventional Commercial Banks of Indonesia. International Research Journal of Business Studies |, 03. https://doi.org/10.21632/irjbs

Su, Moting, Zongyi Zhang, Ye Zhu, Donglan Zha, and Wenying Wen. (2019). "Data Driven Natural Gas Spot Price Prediction Models Using Machine Learning Methods" Energies 12, no. 9: 1680. https://doi.org/10.3390/en12091680

Ereiz, Z. (2019), Predicting Default Loans Using Machine Learning (OptiML), 2019 27th Telecommunications Forum (TELFOR). https://dx.doi.org/10.1109/TELFOR48224.2019.8971110




DOI: http://dx.doi.org/10.35671/telematika.v15i2.1882

Refbacks

  • There are currently no refbacks.




Indexed by:


Telematika
ISSN: 2442-4528 (online) | ISSN: 1979-925X (print)
Published by : Universitas Amikom Purwokerto
Jl. Let. Jend. POL SUMARTO Watumas, Purwonegoro - Purwokerto, Indonesia


Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License .