0. 복습
- Regression : 회귀
- 지도supervised, 비지도 학습unsupervised
1. Machin Learning Algorithm
1) Clustering : Group
2) Reinforcement Learning
3) Data
- Feature
- Label
- Framework
- Open Data : kaggle (Competitions)
4) Orange Data Mining
- GPL License (Open Source Foundation)
- Widget
- Extention
https://www.youtube.com/watch?v=HXjnDIgGDuI&list=PLmNPvQr9Tf-ZSDLwOzxpvY-HrE0yv-8Fy&index=2
5) PyQt
- Qt의 레이아웃에 Python의 코드를 연결하여 GUI 프로그램을 만들 수 있게 해주는 프레임워크.
https://wikidocs.net/book/2944
2. DATA Step: Efficient Data Management and Manipulation
- Title: Improving Customer Retention for an E-commerce Company
First, Understand the Business Domain:
An e-commerce company wants to improve its customer retention rate by identifying the factors that influence customer loyalty. To achieve this, we need to understand the e-commerce industry and how it works. We may need to research customer behavior, sales trends, and industry benchmarks to get a better understanding of the domain.
Second, Understand the Business Problem:
The business problem is that the company's customer retention rate is lower than expected, and they want to identify the factors that influence customer loyalty. We need to define the problem more specifically by asking questions such as: What is the current retention rate? What factors are most important to customers when choosing an e-commerce platform? What are the company's current customer engagement and retention strategies?
Third, What is the Right Data, Right Column and Right Algorithm:
To identify the factors that influence customer loyalty, we need to collect and analyze relevant data. Some potential data sources include customer demographics, purchase history, customer feedback, website traffic, and marketing campaigns. We need to identify the right columns or variables that are most relevant to customer retention. We can then apply various algorithms to analyze the data and identify patterns or correlations between the variables and customer loyalty.
Last, Combine Knowledge With Machine Learning:
Finally, we can use the insights gained from our analysis to develop a customer retention strategy that combines human knowledge with machine learning. For example, we can use predictive models to forecast customer churn and identify high-risk customers who need extra attention. We can also develop personalized marketing campaigns based on customer preferences and behavior. By combining human knowledge with machine learning, we can develop a more effective customer retention strategy that is tailored to the company's specific needs.
3. Data Mining
