Decision tree approach for predicting the credit risk of leasing customers in Sri Lanka

Perera, Prabath

doi:10.1145/3361785.3361797

Cited by 3 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The deep learning model achieved the highest accuracy and highest AROC value with dropouts. Although the developed model achieved a lower accuracy than the model presented in (Perera, 2019), it is more stable due to a higher AROC value. In addition, the developed model has higher capabilities of generalization than the model presented in (Perera, 2019).…”

Section: Deep Learning For Repayment Prediction In Leasing Companies 1144mentioning

confidence: 67%

“…Although the developed model achieved a lower accuracy than the model presented in (Perera, 2019), it is more stable due to a higher AROC value. In addition, the developed model has higher capabilities of generalization than the model presented in (Perera, 2019). It should also be emphasized that the accuracy of the existing model (using in Polish leasing companies based on expert system) is about 0.65 (based on information from BI Technologies sp.…”

Section: Deep Learning For Repayment Prediction In Leasing Companies 1144mentioning

confidence: 67%

“…Our algorithm offers a good balance between profit (from provisions) and loss (from default). The developed model is more precise than the model developed for Sri Lanka (Perera, 2019). The developed model can be used for automatic decision-making by leasing institutions.…”

Section: Discussionmentioning

confidence: 99%

“…(Han, 2019;Jiang, 2018). Only one publication is explicitly dedicated to leasing prediction (Perera, 2019) based on decision trees. The existing general solution for repayment prediction can be, however, insufficient in case of leasing problems.…”

Section: Introductionmentioning

confidence: 99%

“…We explored different scientific databases (google scholar, IEEE Explore, Scopus, Science Direct, SpringerLink, and others), and we found only one work-related to repayment prediction in leasing companies. The work by Perera (2019) presents a model based on a decision tree for predicting the credit risk of leasing customers in Sri Lanka. The accuracy level was 0.92, but the AROC value was only 0.63.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Deep Learning for Repayment Prediction in Leasing Companies

Hernes¹,

Kozierkiewicz²,

Maleszka³

et al. 2021

ERSJ

View full text Add to dashboard Cite

This paper aims to improve repayment prediction in leasing companies using a deep learning model. Design/Methodology/Approach: In this work, we prepare some deep learning models and compare them with other solutions based on artificial intelligence like, multiple regression, decision tree, random forest, and bagging classifier. Findings: The developed model enables automatic analysis of large amounts of data that changes quickly and is often unstructured. Additionally, the input vectors consist of specific attributes related to leasing. The results of experiments allow us to conclude that the prediction accuracy of the developed model is higher than reference models used currently in leasing companies. Practical Implications: The developed model has recently been implemented in the Decision Engine system (a system used by leasing companies in Poland) developed by BI Technologies Sp. Z o.o. Company. Originality/Value: Financial institutions automate and simplify credit procedures, eliminating the analyst from the process and replacing him with automatic decision-making processes based on a scoring or similar models. However, to automatically analyze the significance of phenomena occurring in the environment of organizations that affect the assessment of customer's repayments, it is necessary to use artificial intelligence tools.

show abstract

Section: Deep Learning For Repayment Prediction In Leasing Companies 1144mentioning

confidence: 67%

Section: Deep Learning For Repayment Prediction In Leasing Companies 1144mentioning

confidence: 67%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning for Repayment Prediction in Leasing Companies

Hernes¹,

Kozierkiewicz²,

Maleszka³

et al. 2021

ERSJ

View full text Add to dashboard Cite

show abstract

A Machine Learning Approach to Predict Default Lease Cases in Sri Lankan Financial Institutions

Perera

Kavirathne

Karunathunge

et al. 2022

2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT)

View full text Add to dashboard Cite

Traditional Water Governance Practices for Flood Mitigation in Ancient Sri Lanka

Hewawasam

Matsui

2022

Climate

View full text Add to dashboard Cite

The tank cascade system, which emerged as early as the fifth century BC in Sri Lanka’s dry zone, has been portrayed as one of the oldest water management practices in the world. However, its important function as flood management has not yet been thoroughly examined. In this paper, we argue that the main principle behind the tank cascade system is not only to recycle and reuse water resources by taking advantage of natural landscapes but also to control floods. This paper examines the evolution of traditional water management and flood mitigation techniques that flourished in pre-colonial Sri Lanka. This historical examination also sheds light on recent policies that exhibited renewed interests in revitalizing some aspects of the tank cascade system in Sri Lanka’s dry zone. This paper shows how ancient Sinhalese engineers and leaders incorporated traditional scientific and engineering knowledge into flood mitigation by engendering a series of innovations for land use planning, embankment designs, and water storage technologies. It also discusses how this system was governed by both kingdoms and local communities. Water management and flood control were among the highest priorities in urban planning and management. The paper thus discusses how, for centuries, local communities successfully sustained the tank cascade system through localized governance, which recent revitalized traditional water management projects often lack.

show abstract

Decision tree approach for predicting the credit risk of leasing customers in Sri Lanka

Cited by 3 publications

References 13 publications

Deep Learning for Repayment Prediction in Leasing Companies

Deep Learning for Repayment Prediction in Leasing Companies

A Machine Learning Approach to Predict Default Lease Cases in Sri Lankan Financial Institutions

Traditional Water Governance Practices for Flood Mitigation in Ancient Sri Lanka

Contact Info

Product

Resources

About