Unlock instant, AI-driven research and patent intelligence for your innovation.

Intelligent prediction method based on big data

An intelligent forecasting and big data technology, applied in forecasting, data processing applications, electrical digital data processing, etc., can solve problems such as the lack of public housing rent forecasting means, and the inability of renters to effectively predict market changes, etc., to achieve strong generalization capabilities, The effect of unified model robustness and unified prediction accuracy

Pending Publication Date: 2019-10-25
GUANGDONG UNIV OF TECH
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But at the same time, China's long-term apartment market is also facing multiple challenges such as enterprise market entry, business (store) expansion, capital market games, corporate restructuring and mergers and acquisitions, etc. Among them, how to accurately predict rents has become a major problem in the development process of the industry; The determination of the rent needs to be determined in combination with various factors such as the real estate market, the leasing market, market demand, location and location, and housing configuration. However, there is no means of predicting the rent of relevant houses in the prior art, and the renter cannot effectively predict market changes. , so as to make a reasonable decision

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent prediction method based on big data
  • Intelligent prediction method based on big data
  • Intelligent prediction method based on big data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0022] like Figure 1~5 As shown, an intelligent prediction method based on big data includes the following steps:

[0023] Step 1, data cleaning; preprocessing of raw data, including processing of abnormal data and filling of missing values;

[0024] The specific steps of data cleaning are:

[0025] (1) Abnormal value processing; by drawing scatter diagrams and box diagrams and combining the business meaning of the data itself, abnormal data are eliminated or treated as missing values;

[0026] (2) Fill missing values; empty values ​​of discrete variables are filled with null, and continuous variables are filled with average values;

[0027] Step 2, feature engineering; analyze the cleaned data and find out important features, try to construct a combination of featur...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an intelligent prediction method based on big data. The intelligent prediction method comprises the following steps of step 1, data cleaning; preprocessing the original data; step 2, characteristic engineering; analyzing the cleaned data, finding out important features, and constructing statistical features related to the important features; step 3, constructing a model; anXGboost model, a LightGBM model and a catboost model which are high in classification precision are used for predicting the rent; step 4, model fusion; according to the score of the model predictionresult, different weights are given to the model prediction result, a final model is formed through weighting, and the model generalization ability is improved; and step 5, intelligent prediction; accurate prediction of the rent is realized by utilizing the obtained model; according to the invention, by use of data such as real estate markets, rental markets, market demands and house configuration, by use of model algorithms such as machine learning and artificial intelligence, and in combination with the innovation capability of the model, reasonable house rental prediction is made so as to cope with the influence of market changes on operators and real estate institutions.

Description

technical field [0001] The invention relates to the technical field of big data and machine learning, in particular to an intelligent prediction method based on big data. Background technique [0002] In recent years, the domestic housing rental market has entered a new stage of development, and the long-term apartment market, as an important part of the rental market, has received more and more attention. But at the same time, China's long-term apartment market is also facing multiple challenges such as enterprise market entry, business (store) expansion, capital market games, corporate restructuring and mergers and acquisitions, etc. Among them, how to accurately predict rents has become a major problem in the development process of the industry; The determination of the rent needs to be determined in combination with various factors such as the real estate market, the leasing market, market demand, location and location, and housing configuration. However, there is no mea...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q10/04G06Q30/06G06Q50/16G06F16/215G06N20/00
CPCG06Q10/04G06Q30/0645G06Q50/16G06F16/215G06N20/00
Inventor 刘治孙泽勇章云赖有仿
Owner GUANGDONG UNIV OF TECH