Application of Parallel Random Forest in Doubt Prediction of Audit Big Data

DOI

10.2991/978-94-6463-270-5_42How to use a DOI?

Keywords

Random forest algorithm; Prediction of audit doubt; Hadoop

Abstract

In order to make a scientific audit plan under the background of auditing big data, an audit doubt prediction algorithm based on parallel improved random forest algorithm is proposed. The goal of this algorithm is to improve the efficiency of the algorithm while ensuring the prediction accuracy, so as to meet the needs of big data processing. Firstly, a Hadoop-based big data management scheme for power enterprise audit is established. This scheme can integrate and store heterogeneous audit data from various power grid subsystems. On this basis, a parallel random forest algorithm based on three-layer MapReduce is implemented to predict the probability of audit doubts. Random forest is an integrated learning algorithm, which predicts by constructing multiple decision trees and combining them. In the parallel improvement, a three-layer MapReduce architecture is adopted, which divides the data into multiple sub-data sets and constructs multiple decision trees by parallel computing. Finally, the results of these decision trees are combined to get the final probability prediction result of audit doubt. The experimental results show that the proposed parallel algorithm meets the requirements of big data processing in running speed. At the same time, this algorithm is superior to the commonly used decision tree algorithm in prediction accuracy. This means that the algorithm can not only process a large number of audit data efficiently, but also provide accurate prediction results of audit doubts. Such an algorithm will provide scientific data support for the formulation of audit plans and meet the needs of big data processing.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jing Xiao
AU  - Yi Du
PY  - 2023
DA  - 2023/10/29
TI  - Application of Parallel Random Forest in Doubt Prediction of Audit Big Data
BT  - Proceedings of the 3rd International Conference on Internet Finance and Digital Economy (ICIFDE 2023)
PB  - Atlantis Press
SP  - 378
EP  - 385
SN  - 2667-1271
UR  - https://doi.org/10.2991/978-94-6463-270-5_42
DO  - 10.2991/978-94-6463-270-5_42
ID  - Xiao2023
ER  -