In this research study, we have sought to identify features of drug characteristics and the effectiveness of a prediction model on the price and classification of drugs, using a sample of 37 chronic diseases and their drugs, including drug name/type/form, average price per drug and review, effectiveness score and drug usability and satisfaction levels. The dataset, Drug_clean. Data set in csv format contains information of multiple drugs as well as performance indicators. The method that will be adopted here include pre-processing the data to deal with the missing values and the outliers. Categorical features are pre-processed by performing Label Encoding on them so as to allow for quantitative examination. We perform regression and classification with an aim of predicting the drug price and categorizing types/form of drugs available. For the regression problems we use Linear Regression Model, Decision Tree Regressor, Random Forest Regressor, and XGBoost Regressor. For classification purposes, we use Log Regression, Dec Tree Classifier, Random Forest Classifier, XGBoost Classifier. Decent results are obtained in terms of MAE, MSE, R^2 score for the purpose of price prediction using Random Forest Regressor algorithm. In the drug type classification, Random Forest Classifier and its corresponding ROC AUC results pinpoint how good the model’s performance is in making the differentiation between different drug types. Likewise, the classification of forms of drugs is done by similar models with results accompanied by more comprehensive parameters including accuracy, precision, recall, and F1 Score. Our results depict a favorable work of ENSEMBLE & BOOSTING techniques on continuous & Categorical drug attributes. The paper completes the understanding of how the drug features affect price and classification and may be useful for stakeholders in the industry. This study teaches scholar’s actual drug performance utilizing developed machine learning method and can be a starting for additional analysis and enhancement to different various expert models in pharmacological study and drug launch.