Forest fire forecasting is crucial for resource allocation, mitigation, and recovery. The risk of forest wildfires is rising all around the planet. Large wildfire frequency and area damaged have increased by more than four and six times in the last five decades, respectively. Oxygen, humidity, and temperature are all essential factors in wildfire risk evaluations. A new forest fire risk prediction method is described, which is based on Support Vector Machines, Logistic Regression, KNN, decision trees, and Random Forest. The findings show that forest fire danger can be predicted with reasonable accuracy. So, using machine learning techniques and algorithms such as Logistic Regression, KNN, SVC, Random Forest, and Decision Tree, we proposed a system to predict the percentage of fire occurrence based on various parameters such as temperature, humidity, and oxygen data entered by the user in the front end