Lottery user activity prediction method, system, terminal device, and storage medium

Abstract

The invention discloses a lottery user activity prediction method, which comprises the following steps: acquiring original user data; extracting and converting the original user data; classifying andloading the original user data into a database in a specified format; and loading the original user data into a database in a specified format. Preprocessing the original user data stored in the database to obtain multi-dimensional user data; Obtaining a prediction feature set related to user activity according to the multi-dimensional user data; inputting The prediction feature set into a pre-trained GBDT algorithm-based activity prediction model to predict user activity. Correspondingly, the invention also discloses a lottery user activity prediction system, a terminal device and a computer-readable storage medium. The technical proposal of the invention can reduce the prediction difficulty of the lottery user activity and improve the prediction accuracy.

Description

technical field [0001] The present invention relates to the technical field of data mining, and in particular to a method, system, terminal equipment, and computer-readable storage medium for predicting lottery user activity. Background technique [0002] The turnover of lottery companies is directly linked to the number of users, user activity and betting amount. The lottery industry has a large user base, but user activity is uneven. Highly active users are the main group that contributes to the lottery company's turnover. Identify potential high-growth users and stimulate them to actively participate in the lottery through customer relationship management. Highly active users are gradually gaining attention. [0003] The existing technology provides some technical solutions for user activity prediction, but the existing user activity prediction systems are mainly used in Internet application scenarios such as mobile games, page games, and WEB services. In these applicati...

AI Technical Summary

Problems solved by technology

[0004] Existing models for predicting user activity mainly include rule models based on experience and statistics. For example, users who log in for more than 5 consecutive days are predicted as highly active users. It is difficult to extract accurate rules to predict user activity when the data is complex; regression analysis is widely used in user activity prediction, but it has high requirements for the quality of training data, and it is necessary to exclude the collinearity problem in the independent variables, and reasonably However, the data sources of lottery users are extensive and complex, and there are often exceptions and defaults. Simple regression analysis cannot obtain accurate prediction results.

In addition, the neural network is also a commonly used predictive model. It is a set of connected input / output units, each of which has a weighted value. The classification knowledge of the neural network is reflected in the network connection and is implicitly stored in the connected In the weight value, the learning process of the neural network is a process of continuously adjusting the weight value through iterative operations. The goal of learning is to make the input tuples be correctly labeled through the adjustment of the weight value. The network has a good predictive ability for user activity prediction, but its shortcomings cannot be ignored, such as the black box of the neural network itself, difficult to explain, and high requirements for computing power, which make prediction more difficult

Images