IJSTR >> Volume 9 - Issue 6, June 2020 Edition

[Full Text]

AUTHOR(S)

Pooja Mittal, Dr. Vinod Kr. Srivastava

KEYWORDS

Random Forest, Recall, Precision, Confusion Matrix, F-Score.

ABSTRACT

Credit Balance services play an important role to resolve providers and health care credit balance accounts to recover the overpaid payments and avoid the future errors. This is a critical problem for the health care systems because the accuracy of prediction is very low for identifying the potential overpaid claims where recovery can happen, therefore auditors have to go through all 100% claims, which results in spending lot of time, which cannot yield recovery. To address this problem, this case study will give the ability to health care systems to classify the potential revenue generated claims. We have described and proposed a Random Forest algorithm, which is applied on high dimensional and highly biased data. The proposed Random Forest algorithm has reduced the dimensions by selected the important features and taken care of highly imbalanced data. To classify the overpaid claims, RF has provided a significant improvement over other algorithms such as Decision Tree and Logistic Regression. We have identified the high-ranking features, which influence the credit balance accounts, or claims, which reduce the high dimensionality and enhance performance. This proposed solution offers a new way to help human auditors to focus on revenue generating accounts with high yield and will prevent future errors.

REFERENCES

[1] L. Breiman, “ST4_Method_Random_Forest,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1017/CBO9781107415324.004.
[2] M. Pal, “Random forest classifier for remote sensing classification,” Int. J. Remote Sens., vol. 26, no. 1, pp. 217–222, 2005, doi: 10.1080/01431160412331269698.
[3] G. Cafri, L. Li, E. W. Paxton, and J. Fan, “Predicting risk for adverse health events using random forest,” J. Appl. Stat., vol. 45, no. 12, pp. 2279–2294, 2018, doi: 10.1080/02664763.2017.1414166.
[4] K. Taalab, T. Cheng, and Y. Zhang, “Mapping landslide susceptibility and types using Random Forest,” Big Earth Data, vol. 2, no. 2, pp. 159–178, 2018, doi: 10.1080/20964471.2018.1472392.
[5] A. O. Ok, O. Akar, and O. Gungor, “Evaluation of random forest method for agricultural crop classification,” Eur. J. Remote Sens., vol. 45, no. 1, pp. 421–432, 2012, doi: 10.5721/EuJRS20124535.
[6] J. Evans, B. Waterson, and A. Hamilton, “Forecasting road traffic conditions using a context-based random forest algorithm,” Transp. Plan. Technol., vol. 42, no. 6, pp. 554–572, 2019, doi: 10.1080/03081060.2019.1622250.
[7] W. Mao and F.-Y. Wang, “Cultural Modeling for Behavior Analysis and Prediction,” Adv. Intell. Secur. Informatics, pp. 91–102, 2012, doi: 10.1016/b978-0-12-397200-2.00008-7.
[8] G. Carvajal, M. Maucec, and S. Cullick, Introduction to Digital Oil and Gas Field Systems. 2018.
[9] E. S. Soares, K. P. Oliveira-Esquerre, A. M. de Aguiar, G. L. P. Botelho, and A. Kiperstok, Development of a model to identify combined use in residential water end use events, vol. 44. Elsevier Masson SAS, 2018.
[10] S. Conjeti et al., Domain Adapted Model for In Vivo Intravascular Ultrasound Tissue Characterization, 1st ed. Elsevier Inc., 2017.
[11] E. Iadanza, G. Guidi, and A. Luschi, 7 - Decision Support Systems in Healthcare BT - Clinical Engineering. Elsevier Inc., 2016.
[12] X. Gao, J. Wen, and C. Zhang, “An Improved Random Forest Algorithm for Predicting Employee Turnover,” Math. Probl. Eng., vol. 2019, 2019, doi: 10.1155/2019/4140707.