Statistical model vs machine learning model

• sm can be interpreted by human e.g. doctors interpret arima models.
• ml model is too complicated to be interpreted by human. That's why we let machine create it and call ml model.
• Statistics draws population inferences from a sample, and machine learning finds generalizable predictive patterns. (https://www.nature.com/articles/nmeth.4642)

• The major difference between machine learning and statistics is their purpose. Machine learning models are designed to make the most accurate predictions possible. Statistical models are designed for inference about the relationships between variables. (https://towardsdatascience.com/the-actual-difference-between-statistics-and-machine-learning-64b49f07ea3)

• Decision tree algorithms have been studied throughout machine learning and statistics as a nonparametric approach to data modeling (Breiman, et al., 1984; Quinlan, 1993). Decision tree methodology is often contrasted with classical parametric statistical methodology, which requires the formulation of an explicit probabilistic model of the data generation process. (Cf. M.J. 1994, A Statistical Approach to Decision Tree Modeling) เราสรุปว่า DT เป็น supervised ML model ที่ตีความได้เหมือน statistical model และตอนตีความแต่ละเส้นทางในต้นไม้อาจเห็นโอกาสเกิดปัญหาในอนาคต เช่น เข้าไกล้ leave node ที่เป็นโรคแล้วไหมจะได้ป้องกันเนิ่นๆ

• XAI (Explainable ai) : methods and techniques in the application of artificial intelligence technology (AI) such that the results of the solution can be understood by humans. It contrasts with the concept of the "black box" in machine learning where even its designers cannot explain why an AI arrived at a specific decision. Wikipedia; https://cacm.acm.org/magazines/2022/4/259398-explainable-ai/fulltext#