Legal Judgment Prediction in the Context of Energy Market using Gradient Boosting

被引：0

作者：

Franca, Joao V. F. ^{[1
]}

Boaro, Jose M. C. ^{[1
]}

dos Santos, Pedro T. C. ^{[1
]}

Henrique, Fernando ^{[1
]}

Garcia, Venicius ^{[1
]}

Manfredini, Caio ^{[1
]}

Junior, Domingos A. D. ^{[1
]}

de Oliveira, Francisco Y. C. ^{[1
]}

Castro, Carlos E. P. ^{[1
]}

Braz Junior, Geraldo ^{[1
]}

Silva, Aristofanes C. ^{[1
]}

Paiva, Anselmo C. ^{[1
]}

de Oliveira, Milton S. L. ^{[2
]}

Moreira e Moraes, Renato U. ^{[2
]}

Alves, Erika W. B. A. L. ^{[2
]}

Sobral Neto, Jose S. ^{[2
]}

机构：

[1] Fed Univ Maranhao UFMA, Appl Comp Grp NCA, Sao Luis, Maranhao, Brazil

[2] Equatorial Energy SA, Sao Luis, MA, Brazil

来源：

2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) | 2020年

关键词：

Legal Judgment Prediction; Machine Learning; XGBoost; TPE; SMOTE;

D O I：

10.1109/smc42975.2020.9283297

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

A recurring problem for energy supply companies is the guarantee of the quality of services, which is regulated in many cases. Even so, there are many lawsuits against energy distribution companies, for several reasons, increasing the operating costs of these companies, in many situations with cases that could be resolved via negotiation. This work proposes a method to predict legal judgment outcome regarding the chance of being won or lost by the company. The idea is to understand in which lawsuits more effort should be made to negotiate with the court. The methodology is divided into five stages: feature extraction, sampling with Borderline SMOTE, feature encoding with Target Encoding, classification with XGBoost, and evaluation. The proposed method was evaluated in a database with more than seventy thousand lawsuits, with different outcomes and types, reaching an accuracy of 78.13%, F1 of 74.34%, and AUC of 77.59%.

引用

页码：875 / 880

页数：6

共 50 条

[1] Boosting court judgment prediction and explanation using legal entities
Benedetto, Irene
Koudounas, Alkis
Vaiani, Lorenzo
Pastor, Eliana
Cagliero, Luca
Tarasconi, Francesco
Baralis, Elena
ARTIFICIAL INTELLIGENCE AND LAW, 2024,
[2] Legal Judgment Prediction via graph boosting with constraints
Tong, Suxin
Yuan, Jingling
Zhang, Peiliang
Li, Lin
INFORMATION PROCESSING & MANAGEMENT, 2024, 61 (03)
[3] Enhancing Stock Market Prediction Using Gradient Boosting Neural Network: A Hybrid Approach
Shahin, Taraneh
Heras, Maria Teresa Ballestar de las
Sanz, Ismael
COMPUTATIONAL ECONOMICS, 2024,
[4] Random Forests and Gradient Boosting for Wind Energy Prediction
Alonso, Alvaro
Torres, Alberto
Dorronsoro, Jose R.
HYBRID ARTIFICIAL INTELLIGENT SYSTEMS (HAIS 2015), 2015, 9121 : 26 - 37
[5] Enhancing Link Prediction Using Gradient Boosting Features
Li, Taisong
Wang, Jing
Tu, Manshu
Zhang, Yan
Yan, Yonghong
INTELLIGENT COMPUTING THEORIES AND APPLICATION, ICIC 2016, PT II, 2016, 9772 : 81 - 92
[6] Bioactive Molecule Prediction Using Extreme Gradient Boosting
Mustapha, Ismail Babajide
Saeed, Faisal
MOLECULES, 2016, 21 (08):
[7] The energy efficiency prediction method based on Gradient Boosting Regression Tree
Ma, Hongwei
Yang, Xin
Mao, Jianrong
Zheng, Hao
2018 2ND IEEE CONFERENCE ON ENERGY INTERNET AND ENERGY SYSTEM INTEGRATION (EI2), 2018,
[8] A gradient boosting regression based approach for energy consumption prediction in buildings
Al Bataineh, Ali S.
ADVANCES IN ENERGY RESEARCH, 2019, 6 (02): : 91 - 101
[9] Prediction of home energy consumption based on gradient boosting regression tree
Nie, Peng
Roccotelli, Michele
Fanti, Maria Pia
Ming, Zhengfeng
Li, Zhiwu
ENERGY REPORTS, 2021, 7 : 1246 - 1255
[10] Iceberg draft prediction using gradient boosting regression algorithm
Azimi H.
Shiri H.
Mahdianpari M.
Marine Systems & Ocean Technology, 2023, 18 (3-4) : 151 - 166

← 1 2 3 4 5 →