Development of a Quantitative Prediction Support System Using the Linear Regression Method

Abstract

The development of prediction supports is a critical step in information systems engineering in this era defined by the knowledge economy, the hub of which is big data. Currently, the lack of a predictive model, whether qualitative or quantitative, depending on a company's areas of intervention can handicap or weaken its competitive capacities, endangering its survival. In terms of quantitative prediction, depending on the efficacy criteria, a variety of methods and/or tools are available. The multiple linear regression method is one of the methods used for this purpose. A linear regression model is a regression model of an explained variable on one or more explanatory variables in which the function that links the explanatory variables to the explained variable has linear parameters. The purpose of this work is to demonstrate how to use multiple linear regressions, which is one aspect of decisional mathematics. The use of multiple linear regressions on random data, which can be replaced by real data collected by or from organizations, provides decision makers with reliable data knowledge. As a result, machine learning methods can provide decision makers with relevant and trustworthy data. The main goal of this article is therefore to define the objective function on which the influencing factors for its optimization will be defined using the linear regression method.

Development of Microclimate Data Recorder on Coffee-Pine Agroforestry Using LoRaWAN and IoT Technology

“…To enhance the accuracy and ensure the sensor node readings align more closely with those of the reference tools, calibration is performed using the linear regression method [75]. The linear regression formula, y = mx + c, where y represents the predicted value (reading from the reference instrument), m is the slope of the regression line, x is the independent value (sensor reading), and c is the intercept (yintercept), is employed to ascertain the optimal m and c values that best represent the relationship between the sensor readings and the readings from conventional tools [76].…”