An Improved Gradient Enhancement Regression Tree Method to Evaluate the Innovation Capability of Energy Companies

DOI: https://doi.org/10.62517/jiem.202303402

Author(s)

Zhibo Yu*, Ji Li, Chaohui Gu, Juan Zhou, Mengxi Wu

Affiliation(s)

Research Institute of Natural Gas Economy PetroChina Southwest Oil & Gasfield Company, Chengdu, Sichuan, China *Corresponding Author.

Abstract

In recent years, with the introduction of the innovation-driven development strategy, audit departments across the country have actively responded by arranging audit experts to assess the innovation capabilities of enterprises based on their information. They have also studied the impact of implementation on innovation indicators in energy enterprises, aiming to accurately implements to support enterprises and drive regional development. Traditional manual evaluation methods are inefficient and prone to human interference. By using a gradient boosting regression tree model to construct a scoring prediction model, instead of manual evaluation methods, both accuracy and efficiency can be ensured. Experimental results show that this prediction model outperforms other models such as random forest regression and can guarantee prediction accuracy.

Keywords

Innovation Capability; Gradient Boosting; Ensemble Learning; Machine Learning

References

[1]Kaichao Shao, Xiaohua Wang. Do government subsidies promote enterprise innovation? —Evidence from Chinese listed companies. Journal of Innovation & Knowledge, 2023, Vol. 8(4): 100436. [2]Li Qing, Wang Maoqiong, Liuxu Xiang Li. Do government subsidies promote new-energy firms’ innovation? Evidence from dynamic and threshold models. Journal of Cleaner Production, 2020, Vol.286: 124992. [3]Sun J, Long J. Will R&D Expenses and Deduction Policies Promote Company Innovation? World Scientific Research Journal, 2019, 5(9):147-152. [4]Friedman J, Hastie T, Tibshirani R. Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). The annals of Statistics, 2000, 28(2): 337-407. [5]Ting Lu, Xiaoang Zhai, Sihui Chen, et al. Robust battery lifetime prediction with noisy measurements via total-least-squares regression, Integration, 2024, 96: 102136. [6]Ziwen Gu, Yatao Shen, Zijian Wang et al. Wind speed prediction utilizing dynamic spectral regression broad learning system coupled with multimodal information. Engineering Applications of Artificial Intelligence, 2024, Vol.131: 107856. [7]Mohammad Abdullah Abid Almubaidin. Enhancing sediment transport predictions through machine learning-based multi-scenario regression models. Results in Engineering, 2023, Vol.20: 101585. [8]Dietterich T G. Ensemble learning. The Handbook of Brain Theory and Neural Networks, 2002, 2:110-125. [9]Klaus Nordhausen. Ensemble Methods: Foundations and Algorithms. International Statistical Review, 2013, Vol. 81(3): 470. [10]Whittington J C R, Bogacz R. Theories of error back-propagation in the brain. Trends in Cognitive Sciences, 2019, 23(3): 235-250. [11]Cortes C, Vapnik V. Support vector machine. Machine Learning, 1995, 20(3): 273-297. [12]Freund Y. Boosting a weak learning algorithm by majority. Information and Computation, 1995, 121(2): 256-285. [13]Breiman L. Bagging predictors. Machine Learning, 1996, 24(2): 123-140. [14]Wang Guoqing, Ruan Yuling, Wang Hongxing et al. Tribological performance study and prediction of copper coated by MoS2 based on GBRT method. Tribology International, 2023, Vol.179. [15]Kamal W A , H. S E , Sameer A , et al. Development of GBRT Model as a Novel and Robust Mathematical Model to Predict and Optimize the Solubility of Decitabine as an Anti-Cancer Drug. Molecules, 2022, 27(17): 5676-5676. [16]Song J, Jinyuan L, Sai Z, et al. Landslide risk prediction by using GBRT algorithm: Application of artificial intelligence in disaster prevention of energy mining. Process Safety and Environmental Protection, 2022, 166: 384-392.