Programming groups benefit significantly from programming error forecasting, which also advances current achievement. Programming imperfection expectation has been the subject of experimental studies on both inside- and outside-project deformity forecast. However, current analyses dont appear to be able to provide a method for estimating the number of flaws in a soon-to-be-released product. This paper describes such an approach and determines the relationship between each indicator variable and the total number of defects using indicator variables obtained from the deformity speed increase, namely the imperfection thickness, deformity speed, and imperfection presentation time. We describe how a coordinated AI strategy was used in light of relapse models created using these indicator criteria. 3 distinct datasets with 228 occurrences were taken from the Kaggle store and subjected to analysis. The modified R-square for the relapse model developed as a component of the usual deformity speed was 98.6%, with a p-value of 0.001 being achieved. With a connection value of 0.98, the average deformity speed is clearly correlated with the number of flaws. As a result, it is demonstrated how this process might provide a framework for programmer testing in order to increase the viability of programming advancement activities.