Typical data mining and machine learning processes
Figure 1 is a typical recommendation class application that needs to find a "qualified" potential person. To draw this list from the user data, we first need to dig out the customer characteristics, then select a suitable model to predict, and finally draw the result from the user data.
The user list acquisition process in the above example is subdivided into the following sections (see Figure 2):
Business Understanding: Understanding the business itself, what is its essence. Is the problem of classification or regression. How to get the data. Which models are applied to resolve.
Data understanding: After obtaining the data, analyze the data inside what content, the data is accurate, prepares for the next pretreatment.
Data preprocessing: The original data will be noisy, format is not good, so in order to ensure the accuracy of the prediction, the need for data preprocessing.
Feature extraction: Feature extraction is one of the most important and time-consuming stages of machine learning.
Model building: Use the appropriate algorithm to get the expected exact value.
Model evaluation: Evaluate the accuracy of the model according to the test set.
Model application: Deploy the model and apply it to the actual production environment.
Application Effectiveness Assessment: Evaluate the final application results based on the final business.
best practice of constructing high performance neural network model under 1.TensorFlow 2.TensorFlow Core Process Analysis-construction, segmentation and optimization of neural network model configuration under the 3.pycharm under TensorFlow