인공지능 기법 비교를 통한 개인소득 예측 모델 성능 평가
Evaluation of Personal Income Prediction Models through Comparative Analysis of AI Techniques
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 연구는 인구통계 데이터를 활용해 개인 소득을 예측하고, 다양한 머신러닝 및 인공지능 기법의 성능을 비교하였다. 개인 소득 예측은 금융기관의 대출 심사, 타겟 마케팅, 신용 평가와 같은 실무적 활용뿐만 아니라, 소득 불균형 해소와 세제 설계 등 정책 수립 과정에서도 중요한 역할을 한다. 본 연구는 2001년 미국 인구통계 데이터에서 30,000개의 샘플을 추출해 분석에 활용하였다. 소득 예측에 적용된 기법으로는 선형 회귀분석, 의사결정 나무, 랜덤 포리스트, 인공신경망, 그레디언트 부스팅 등 5가지를 사용했으며, 각 기법의 성능은 10-fold 교차 검증을 통해 평가했다. 분석 결과, 인공신경망이 다른 기법에 비해 가장 높은 예측 정확도를 보였으며, Wilcoxon 검정을 통해 통계적으로도 우수함을 확인했다. 본 연구는 소득 예측 문제에 다양한 기법을 적용하여 비교했다는 점에서 학문적으로 의미가 있으며, 금융기관과 정책 입안자들이 보다 정확하고 신뢰할 수 있는 소득 예측 모델을 활용하는 데 기여할 수 있다.
Abstract
The purpose of this study is to predict personal income using demographic data and compare the performance of machine learning techniques. Income prediction has practical applications in loan approval, marketing, and credit evaluation, as well as addressing income inequality in policymaking. Using 30,000 samples from the 2001 U.S. demographic dataset, five methods—linear regression, decision tree, random forest, neural networks, and gradient boosting—were evaluated. Neural networks showed the highest accuracy, confirmed through Wilcoxon analysis. This study provides valuable insights for adopting accurate income prediction models.
참고문헌 (31)
- G. Shmueli, "Predictive analytics in information systems research", MIS quarterly, 35(3), pp.553~572 (2011)
- G. Athanasopoulos, "Forecast reconciliation : A review", International Journal of Forecasting, 40(2), pp.430~456 (2023)
- R. Chetty, "The economic impacts of COVID-19 : Evidence from a new public database built using private sector data", The Quarterly Journal of Economics, 139(2), pp.829~889 (2024)
- A. Mann, "Reducing Hospital Readmission Risk Using Predictive Analytics", INFORMS, Interfaces, 54(4), pp.380~388 (2024)
- D. R. Deepa, "Early prediction of cardiovascular disease using machine learning : Unveiling risk factors from health records", AIP Advances, 14(3), pp.035049~035049-20 (2024)
- H. Wei, "Framework for integrating trafficsource emission estimates into sustainability analysis", CICTP 2012: Multimodal Transportation Systems—Convenient, Safe, Cost-Effective, Efficient, 9, pp.3612~3619 (2012)
- M. Sri Darshan, "Integrating Data Mining and Predictive Modeling Techniques for Enhanced Retail Optimization", International Journal of Computer Science and Information Security(IJCSIS), 22(5), pp.1~5 (2024)
- T. Zhang, "Multiple instance learning for credit risk assessment with transaction data", Knowledge-Based Systems, 161, pp.65~77 (2018)
- B. Liu, "Factorizing historical user actions for next-day purchase prediction", ACM Transactions on the Web(TWEB), 16(1), pp.1~26 (2021)
- S. Adinarayana, "A MACHINE LEARNING APPROACH TO PREDICT BLACK FRIDAY SALES", International Journal of Engineering Research and Science & Technology, 20(2), pp.143~156 (2024)
- J. Bauer, "Improved customer lifetime value prediction with sequence-tosequence learning and feature-based models", ACM Transactions on Knowledge Discovery from Data(TKDD), 15(5), pp.1~37 (2021)
- A. Vankevich, "Ensuring sustainable growth based on the artificial intelligence analysis and forecast of in-demand skills", E3S web of conferences, 208, pp.03060~ (2020), EDP Sciences
- J. C. Valverde-Rebaza, "Job Recommendation Based on Job Seeker Skills: An Empirical Study", Text2Story@ ECIR, pp.47~51 (2018)
- C. Van Hoof, "The virtual personal health coach : Technology and data analytics join forces to disrupt preventive health", 2017 7th IEEE International Workshop on Advances in Sensors and Interfaces(IWASI), pp.233~233 (2017)
- J. Coelho, "A personalized travel recommendation system using social media analysis", 2018 IEEE International Congress on Big Data (BigData Congress), pp.260~263 (2018), IEEE
- K. A. Srivastava, "Geo-Intelligence and Visualization through Big Data Trends", pp.76~93 (2015), IGI Global
- S. R. Baker, "Household financial transaction data", Annual Review of Economics, 14(1), pp.47~67 (2022)
- Z. Jiang, "Prediction and industrial structure analysis of local GDP economy based on machine learning", Mathematical Problems in Engineering, 2022(1), pp.7089914~ (2022)
- D. Yamamoto, "Scales of regional income disparities in the USA, 1955–2003", Journal of Economic Geography, 8(1), pp.79~103 (2008)
- Z. Yu, "Error correction method based on data transformational GM(1, 1)and application on tax forecasting", Applied Soft Computing, 37, pp.554~560 (2015)
- A. Kalinin, "Discovering patterns of customer financial behavior using social media data", Social Network Analysis and Mining, 10(1), pp.77~ (2020)
- J. R. Quinlan, "Induction of decision trees", Machine learning, 1, pp.81~106 (1986)[DOI]
- K. Stoffel, "Selecting optimal split-functions for large datasets", Research and Development in Intelligent Systems XVII: Proceedings of ES2000, the Twentieth SGES International Conference on Knowledge Based Systems and Applied Artificial Intelligence, pp.62~72 (2001), Springer
- H. Ishwaran, "Variable importance in binary regression trees and forests", Electronic Journal of Statistics, 1, pp.519~537 (2007)
- L. Breiman, "Random forests", Machine learning, 45, pp.5~32 (2001)
- J. H. Friedman, "Greedy function approximation: a gradient boosting machine", Annals of statistics, pp.1189~1232 (2001)
- Y. Pristyanto, "Extreme Gradient Boosting Algorithm to Improve Machine Learning Model Performance on Multiclass Imbalanced Dataset", International Journal on Informatics Visualization, 7(3), pp.710~715 (2023)
- D. R. Cox, "Two further applications of a model for binary regression", Biometrika, 45(3, pp.4) (1958), 562~565
- F. S. De Menezes, "Data classification with binary response through the Boosting algorithm and logistic regression", Expert Systems with Applications, 69, pp.62~73 (2017)
- D. E. Rumelhart, "Learning representations by backpropagating errors", Nature, 323(6088), pp.533~536 (1986)
- Y. LeCun, "Gradient-based learning applied to document recognition", Proceedings of the IEEE, 86(11), pp.2278~2324 (1998)
