Machine-learning; Social Security Big Data; Predictive model
The core technology of the Fourth Industrial Revolution is artificial intelligence and big data, and the continuous enhancement of algorithm performance through Machine Learning based on large scale accumulated data is an mportant source technology in all fields. Machine Learning is a field of AI that develops algorithms and techniques that enable computers to learn based on data. It is a core technology in various fields such as image processing, image recognition, speech recognition, and Internet search. The results show excellent performance in predication. In this study, we study the characteristics of Social Security Big Data which is being produced in Korea and study Machine Learning statistical techniques. We design a Machine Learning-based prediction model suitable for Social Security Big Data analysis and present a methodology that can be applied to evidence-based research. Machine Learning-based prediction model can provide a basis for presenting academic and policy implications by ontributing to the utilization of data and making various analysis possible to derive new value. Machine learning can be applied to the field of social policy in which vast amounts of data are accumulated, and Machine Learning-based statistical analysis will be able to approach the predictable customized welfare.
Ⅰ. Introduction 1 Ⅱ. Concepts 5 1. Social Secunity Big Data 7 2. Machine Leaming 9 3. Machine Learning Algorithms 11 Ⅲ. Methods 13 1. Statistical Techniques of Machine Learning: Pros and Cons 15 2. Model Evaluation 17 Ⅳ. Results 21 1. Establishing a Database for Analysis Using a Predictive Model for Social Security Benefits 23 2. Results 25 3. Chapter Conclusion 29 Ⅴ. Conclusion and Policy Implications 33 References 39