APPLICATION OF MULTIPLE LINEAR REGRESSION ESTIMATING THE POPULATION OF ASAHAN REGENCY

: Population is a group of people who live or settle in an area for six months or more. Increasing the population in an area results in more problems being faced by the area such as high unemployment rates, poverty and food shortages which result in hunger. BPS Asahan Re-gency records that there is an increase in population every year. Asahan Regency BPS cannot predict population growth in the following year, so an application is needed to predict population growth. The purpose of this study is to predict population growth in Asahan Regency in the following year based on previous data using the concept of data mining. By applying data mining using multiple linear regression methods can be used to calculate population growth estimates based on previous data. This quantitative research used population data of Asahan Regen-cy from 2016 to 2022. From the calculation of the multiple linear regression model using data from the previous five years, the estimated population growth of Asahan for 2023 was 824,617 people and the process of estimating the population became more systematic and calculated. well with this population estimation system and the process of storing data becomes easier and does not require a lot of paper to print and save.


INTRODUCTION
Residents are a group of people who live or live in an area for six months or more and people who stay for less than six months but have the intention of settling in the area.Residents are people who live in a place, its mean that the population is a group of people who live in an area [1].
The more the population of an area, the higher the changes in the area and the more problems faced by a region.A population growth rate that is too high will risk causing various problems for the area, such as high unemployment rates, poverty and food shortages which lead to hunger.Factors that influence population growth include: births (fertility), deaths (mortality) and also population migration.Continuously the population will be affected by the increase in the number of births (fertility), but simultaneously it will also be reduced by the number of deaths (mortality) that occur in all age groups [2].
BPS has the duty and function of collecting statistical data on the population from year to year.The use of this data collection is for country data collection for the needs of economic strategy, infrastructure, and so on.So that the BPS institution can predict the estimated population growth which is calculated using the geometric method and calculated using Microsoft Excel so that the data is not stored in the database but in the excel file itself.
Population projection using the geometric method uses the assumption that the population will increase geometrically using a compound calculation basis with the population growth rate (rate of growth) considered the same for each year [3].
Data mining process of extracting information from large data sets using algorithms and drawing techniques from statistics, machine learning and database management systems [4] [5].Data mining which is also known as Knowledge Discovery in Database (KDD) is an automatic process of searching data in a very large memory of data to find out patterns by using tools such as classification, association or clustering [6] [7].
Data mining can be used to calculate population growth estimates [8].The method used to calculate is Multiple Linear Regression.Multiple Linear Regression is an analysis that has more than one independent variable [9].Multiple Linear Regression Techniques are used to determine whether there is a significant effect of two or more independent variables (X1, X2, Xn) on the dependent variable (Y) [10].
In this study, the area whose population you want to know is Asahan District.Based on data on the number of residents in the Central Statistics Agency (BPS) of Asahan Regency, it can be seen that there is a difference in the number of residents each year.Every year the population of Asahan Regency always increases.Because every year the population in Asahan Regency is increasing, the authors are interested in estimating the population of Asahan Regency.Population estimation is not a forecast but a scientific calculation based on assumptions about the growth rate component [11] [12].
To estimate a population or total population, it can be done by using a model whose results are close to the population data held by the Central Bureau of Statistics (BPS).To estimate the population, one of the models used is the Multiple Linear Regression model.In the case of this population, the Multiple Linear Regression model is used to find out the population of Asahan Regency in 2023.
The purpose of this research is to find out how to use the multiple linear regression method to estimate the population and with the concept of data mining using multiple linear regression to estimate the population in the following year using a web-based application.
Research conducted by [13] with the title Application of Data Mining to Estimate Population Growth Rates Using Multiple Linear Regression Methods at BPS Deli Serdang concludes that the multiple linear regression method can help BPS to find out what attributes/criteria affect the rate of population growth .And also found patterns that are closely related between the attributes of the number of men and the number of women to the rate of population growth.
While the research entitled Multiple Linear Regression Analysis in Estimating Rice Productivity in Karawang Regency Tesa conducted by [14] concluded that the regression model obtained, amounting to 80.46%, rice productivity factors can be explained by production, harvested area, planting area , rainfall, and rainy days.While the remaining 19.54% can be explained by other factors not examined in this study.The variables that affect the increase in total productivity of rice are production and rainfall variables, while the variables that affect the decrease in total productivity are harvested area, planted area, and rainy days.The average regression relative error obtained is or 4.642%.
Subsequent studies examined by [15] with the title Prediction of Increase in Sales Turnover Using Multiple Linear Regression Methods found that data mining using multiple linear regression methods calculates the equation and then produces the desired sales prediction.
The system created can be used to predict an increase in sales turnover using multiple linear regression methods with fairly accurate results.

METHOD
This study uses quantitative research methods conducted on BPS Office Jl.Tusam No. 2, Kisaran, Mekar Baru, Kec.Kota Kisaran Barat, Kabupaten Asahan, Sumatera Utara 21216.The data collection technique was carried out by literature study by studying journals, books and previous research, the following were interviews with BPS members and direct observation of the research location.
The multiple linear regression model is an equation that describes the relationship between two or more independent variables (X1, X2,…Xn) and one dependent variable (Y).The purpose of multiple linear regression analysis is to predict the value of the dependent variable (Y) if the values of the independent variables or predictors (X1, X2, ..., Xn) are known and also to find out the direction of the relationship between the dependent variables.independent with independent variables.Multiple linear regression equations can be calculated using the formula [15]: Where : Y = dependent variable (value to be predicted) a = constant b1, b2,.., bn = regression coefficient X1, X2,…, Xn = independent variable

RESULTS AND DISCUSSION
For the calculation of multiple linear regression, initial data is needed, namely the population data.Here is the-population data used: Then enter the numbers that have been obtained in Tables 3 and 4 and the values from table 2 so that the value a = - 968.26 is obtained, the value of b1 = 3.277 and the value of b2 = 1,311.And produce a regression equation y = a + b1.x1 + b2.x2 = -968,26 + (3,277 * 393,392) + (1,311 * 384,234) = -968,26 + 1289,146 + 503,731 = 824,617 x 1000 = 824.617People Application View Image 1. Login Page A username and password are needed so you can enter the page, for example entering as an officer or admin.Image 2. District Data

Table 1 .
Population DataBecause in multiple linear regression calculations a lot of multiplication and exponents are carried out, to simplify the numbers will be divided by 1000 and this table determines X1 (men), X2 (woman) and Y (total population) so as to produce the following table: