Against the backdrop of the booming development of the digital economy, this article delves into the importance of evaluating the value of data assets, pointing out that as the digital economy becomes a new driving force for national economic development, the status of data as a production factor is highlighted and transformed into an important asset. However, the current accounting system's inclusion of data assets is not yet complete, which limits the accurate measurement of data value and its economic contribution, and affects the healthy development of the data trading market. The theoretical contribution of this article lies in the comprehensive analysis of the influencing factors of data asset value using B-P neural network and random forest algorithm, and the construction of a high prediction accuracy evaluation model. It was found that data capacity, size, quality, freshness, and industry all significantly affect its value, with the random forest model being preferred due to its advantages. This study not only enriches the theoretical system but also provides new ideas for practical applications. The established model can guide data asset evaluation, support market fair trading and resource optimization allocation, and propose policy recommendations to promote data quality improvement, market perfection, and value maximization. However, research also faces challenges such as single data sources and limited data types. In the future, it is necessary to expand data sources, explore nontextual numerical data evaluation methods, and introduce more advanced technologies to more comprehensively and accurately evaluate the value of data assets, promote the improvement and development of the data factor market, and assist in the digital transformation of the economy.

Yijiao Fan. Research on Data Asset Feature Analysis and Value Evaluation Strategy Based on Random Forest and B-P Neural Network. Academic Journal of Business & Management (2024) Vol. 6, Issue 11: 42-46. https://doi.org/10.25236/AJBM.2024.061107.

[1] Uusitalo T, Hanski J, Kortelainen H, et al. Real Value of Data in Managing Manufacturing Assets. IEEE, 2021. DOI: 10. 1007/978-3-030-64228-0_15.

[2] Jinmao L. Innovative Thinking on Development of Internal Audit of Commercial Banks in the New Era. Journal of Finance and Accounting, 2021, (3). DOI: 10. 11648/J. JFA. 20210903. 13. 

[3] Shehab M F, Mohamed M. A. El-Sheikh, Hamdy M. AhmedAmina A. G. MabroukM. MirzazadehM. S. Hashemi. Solitons and other nonlinear waves for stochastic Schrdinger-Hirota model using improved modified extended tanh-function approach. Mathematical Methods in the Applied Sciences, 2023, 46 (18): 19377-19403. DOI: 10. 1002/mma. 9632. 

[4] Karic K, Blagojevic M. Statistical analysis of ISO/IEC and IEEE standards in the field of artificial intelligence, machine learning and data mining. IEEE, 2021. 

[5] Du Q, Zhai J. Application of artificial intelligence Sensors based on random forest algorithm in financial recognition models. Measurement: Sensors, 2024, 33. DOI: 10. 1016/j. measen. 2024. 101245. 

[6] Kumar S, Garg C, Vashisht P. Method and System for Improved Consensus Using Bootstrap Resampling [P]. US202016884579. US2021374125A1 [2024-07-13]. 

[7] Koapaha H P, Ananto N. Bagging Based Ensemble Analysis in Handling Unbalanced Data on Classification Modeling. Klabat Accounting Review, 2021. DOI: 10. 60090/kar. v2i2. 589. 165-178. 

[8] Mourad N. Robust smoothing of one-dimensional data with missing and/or outlier values. IET signal processing, 2021, (5): 15. 

[9] Envelope F M O A. Multiple Linear Regression Model for Improved Project Cost Forecasting. Procedia Computer Science, 2022, 196: 808-815.