A Method for Forecasting Website Visits Based on Historical Trend Weight
A technology of website visits and prediction methods, which is applied in the field of website visits prediction based on historical trend weights, and can solve problems such as large deviations in estimated values, no solutions, and magnified trends during the period
Active Publication Date: 2016-12-28
BEIJING QIERBULAITE TECH
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
If the trend regression of the historical trend is carried out in multiple cycles, the trend during the cycle will be enlarged; and the "experience library" of the historical trend is not well utilized, and it is impossible to find a suitable example from the "experience library" as a forecast reference
If K-nearest neighbors are used for prediction, when the distribution of surrounding neighbors is uneven, the deviation of the estimated value will be large
[0005] At present, there is no effective solution in the prior art
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0034] In order to better understand the technical problems solved by the present invention and the technical solutions provided, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The specific embodiments described here are only used to explain the implementation of the present invention, but not to limit the present invention.
[0035] In a preferred embodiment, figure 1 It exemplarily shows the flow of a method for predicting website visits based on historical trend weights;
[0036] Use the PV data of a certain period of time to illustrate the prediction effect. The historical data is 29 days, and 36 consecutive PV values are taken out every day. The current 30 PV values are known, and the next 6 PV values are predicted.
[0037] 1. As shown in Table 1: Take 36 consecutive PV values every day in the past 29 days, and the time interval is one every 5 minutes;
[0038] Table 1. Historical 2...
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
Login to View More Abstract
The invention relates to the technical field of statistical analysis of website data, and specifically discloses a method for predicting website visits based on historical trend weights; data preprocessing takes logarithm of visits, calculates the variance of each time point of the historical trend, and calculates the i-th Calculate the regression coefficient of the historical trend to the current trend, calculate the variance of the correlation coefficient of the current value estimated by the i-th historical trend, use the optimization and minimization method to estimate the deviation to solve the weight, predict the value after the current trend according to the weight, and process the predicted result to convert the predicted result Do an exponential transformation. The present invention compares the known current trend with the historical trend, calculates the correlation coefficient, estimates the deviation of the current trend according to each historical trend, selects the weight of each historical trend with an optimization method, and calculates the estimation of each date according to the weight Superimposed, the superimposed results can predict the current and subsequent trends, so that the deviation of the current trend from the comprehensive historical trend is estimated to be the smallest, and a more reliable forecast can be obtained.
Description
technical field [0001] The invention relates to the technical field of statistical analysis of website data, in particular to a method for predicting website visits based on historical trend weights. Background technique [0002] Website traffic refers to website traffic, which is used to describe indicators such as the number of users visiting a website and the number of pages browsed by users. Commonly used statistical indicators include the number of independent users of the website, the number of total users, the number of web pages viewed, and the number of pages viewed by each user. The number of page views, the average stay time of users on the website, etc. Page views, also known as page views, English Page View, referred to as PV, is one of the most commonly used indicators for evaluating website traffic. Usually used to measure the website traffic of an online news channel or website or even a piece of online news. Monitoring the change trend of website PV, analy...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/04G06F17/30
Inventor 胡勇
Owner BEIJING QIERBULAITE TECH