Dengue is a viral disease caused by the Aedes species mosquitoes to people. It mostly occurs in subtropical and tropical climates. It might have mild and worsened symptoms such as headache, nausea, high fever, body aches, and rashes. Some patients recovered from this disease without any medical and some undergo severe treatment and some may loss their lives. It gets worsen with climatic change and early forecasting is an important factor for the forecasting of Dengue. This work focuses to forecast dengue from four cities in India: Chennai, Hyderabad, Bangalore, and Mumbai. Moreover, we propose machine learning approaches such as Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and Logistic regression (LR) methods and compared them with state-of-art works on weather-based Dengue disease forecasting. Monthwise dengue patients and related rates in different cities in India are provided by the National Vector Borne Disease Control Program (NVBDCP). Here, we have taken the data’ from four cities namely Chennai, Hyderabad, Bangalore, and Mumbai in which the dataset used in forecasting includes the fields such As City, Month, Year, Normalized Difference Vegetation Index (Ndvi) (NDVI NE Northeast, NDVI NW Northwest, NDVI SE Southeast, NDVI SW Southwest), Humidity (%), Air Temperature (Minimum, Maximum and Average), Precipitation (Rainfall in mm), Dew Factor (Dew Point Temp). For analysis, we have collected data from the four cities and conducted it over the JAVA simulator. The proposed work is compared with state-of-art works in terms of Root Mean Square (RMSE), Mean Absolute Error (MAE), and Mean Squared Error (MSE). The proposed work surpasses all the other approaches and helps in accepting the forecasting outcomes.