Advertisement

Extrapolation and Visualization of NPA Using Feature Based Random Forest Algorithm in Indian Banks

  • J. Arthi
  • B. Akoramurthy
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 710)

Abstract

The instigation of Non-Performing Assets (NPAs) in Indian banks was post 2009, when world was doing quantitative easing (QE) to save them off recession in 2008. The problem of NPA in India has witnessed the gross NPA rise to 79.7% and net NPA from 2.8% in September 2015 to 4.6% in March 2016. Banking has its NPA data increasing year by year which is a serious concern for the Indian banks. In this paper, an algorithm to determine and predict NPA is proposed. The proposed algorithm creates a pattern based on NPA data sets from various banks, and features are extracted to predict and eradicate financial debts. Also, a visual banking dashboard is developed exclusively for NPAs. The learning task in the proposed Feature based Random Forest algorithm is carried out by incorporating features extracted from the dataset considered and hence improves the prediction accuracy. The result of prediction is visualized using Tableau which, not only provides insights on the data but also aids in data-driven decision making.

Keywords

NPA Data visualization Random forest algorithm Prediction 

References

  1. 1.
    Siraj, K. K., and P. Sudarsanan Pillai. “Comparative study on performance of Islamic banks and conventional banks in GCC region.” Journal of Applied Finance and Banking 2.3 (2012): 123.Google Scholar
  2. 2.
    Ramu, N. “Dimensions of non-performing assets in urban cooperative banks in Tamil Nadu.” Global Business Review 10.2 (2009): 279–297.Google Scholar
  3. 3.
    Veena, D., and GV Bhavani Prasad. “Asset Quality Management in Indian Banks-A Study of SBI & ICICI.” (2014).Google Scholar
  4. 4.
    Flood, Mark D., et al. “The application of visual analytics to financial stability monitoring.” Journal of Financial Stability 27 (2016): 180–197.Google Scholar
  5. 5.
    Tanaka, Katsuyuki, Takuji Kinkyo, and Shigeyuki Hamori. “Random forests-based early warning system for bank failures.” Economics Letters 148 (2016): 118–121.Google Scholar
  6. 6.
    Kumar, P. Ravi, and Vadlamani Ravi. “Bankruptcy prediction in banks and firms via statistical and intelligent techniques—A review.” European journal of operational research 180.1 (2007): 1–28.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Kongu Engineering CollegePerunduraiIndia
  2. 2.IFET College of EngineeringVillupuramIndia

Personalised recommendations