Raqamli texnologiyalarning Yangi O‘zbekiston rivojiga ta’siri

Basic 3 ML algorithms which provide GDP forecasting 
Linear Regression:
In statistics linear regression is a linier approach for modelling the 
relationship between a scalar response and one or more explanatory variables. The case of one 
explanatory variable is called simple linier regression; for more than one, the process is 
called multiple linier regression
.
This term is distinct from multivariate linier regression, where 
multiple corrected dependent variables are predicted, rather than a single scalar variable. In linear 
regression, the relationships are modeled using linier predictor functions whose unknown 
model parameters are estimated from the data. 
1
The linear predictor function is represented as: 
𝑌 = 𝛽
0
+ 𝛽
1
𝑋
1
+ 𝛽
2
𝑋
2
+ ⋯ + 𝛽
𝑛
𝑋
𝑛
+ 𝜀
1
https://en.wikipedia.org/wiki/Talk:Linear_regression

---

12 
 
RAQAMLI TEXNOLOGIYALARNING 
YANGI 
O‘ZBEKISTON
 RIVOJIGA 
TA’SIRI
 
Xalqaro ilmiy-amaliy konferensiyasi
 
where: 
𝑌
–
is the dependent variable 
𝑋
1
, 𝑋
2
, … , 𝑋
𝑛
–
are the independent variables 
𝛽
0
, 𝛽
1
, 𝛽
2
, … , 𝛽
𝑛
–
are the coefficients that represent the relationship between the variables 
𝜀
–
is the error term that captures the deviations between the observed values and the predicted 
values 
The goal of linear regression is to estimate the values of the coefficients based on the 
available data. This estimation is typically done using methods such as ordinary least squares (OLS), 
which minimizes the sum of squared differences between the observed values and the predicted 
values. Linear regression is widely used in various fields for tasks such as prediction, forecasting, 
and understanding the relationship between variables. It provides interpretable coefficients that 
allow for assessing the impact and significance of each independent variable on the dependent 
variable.