Aim: The main objective of the research study is to improve the accuracy for Medical costs for Health Insurance using Polynomial Regression Algorithm compared with Lasso Regression Algorithm. Materials and Methods: The dataset needed for the Medical cost prediction for health insurance is acquired from Google’s Kaggle Website. The data set columns have the columns patient name, age, sex, bmi, smoker, children, region. In these features insurance charges are dependent variables and the remaining features are called independent variables. In regression analysis, predict the values of dependent variables using independent variables. The data sets are imported and Polynomial regression Algorithm and Lasso regression Algorithms are tested. The number of groups are 2 for two Algorithms with the G-power value of 80%. The sample size is 20 per group. Results: The results are acquired in the form of accuracy for the inputs provided. The IBM SPSS tool is used in order to obtain the results. From these results the author has obtained, statistical significance difference was observed between the Polynomial Regression and has an accuracy of 83.94% and Lasso Regression Algorithm 75.06%, which is more accurate than the value. The independent sample T-Test was performed to find the mean, standard deviation, standard error mean significance between the groups.The study has a significance value of p=0.001 (p<0.05) two-tailed. Conclusion: In this paper, based on the results obtained, the Polynomial Regression Algorithm has more accuracy than Lasso Regression Algorithm.