Flooding, one of the most devastating natural disasters, is primarily caused by excessive rainfall that exceeds the drainage capacity of land. Palakkad district in Kerala, India, serves as the focal point of this study, which investigates the flood risk by analyzing spatial factors as rainfall, elevation, land use and land cover, and soil type using Geographic Information Systems (GIS) and machine learning techniques. The district is characterized by diverse topographies and varying rainfall patterns, which significantly influence the flood risk. The research employs Shuttle Radar Topography Mission, Digital Elevation Models, rainfall data from the Kerala Water Resources Information System (WRIS), and soil maps sourced from the FAO to prepare thematic maps of elevation, soil types, and Land Use-Land Cover. Additionally, the research applies an Inverse Distance Weighting (IDW) method for interpolating rainfall data across the 17 blocks of the district and utilizes machine learning (Random Forest regression) to predict the normal rainfall for 2025. Flood vulnerability results showing that approximately 61.94% of the district is classified under high-risk flood zones, particularly in urban and developed areas. Soil types such as Lithosols and Acrisols were found to have high infiltration rates, contributing to significant flood risks Elevation analysis showed that lowlands, particularly in river proximity, and waterfalls are the most vulnerable places for flood hazard. LULC mapping showed that urban areas and water bodies are the most vulnerable to flood hazards due to the lack of water infiltration. 2025 normal rainfall prediction also showed spatial heterogeneity in rainfall with high rainfall being predicted in places like Sreekrishnapuram and Mannarkad, which could exacerbate the flood hazards in those areas. The study concludes by proposing a complete flood hazard map, which is a very essential tool for future flood management, disaster preparedness, and resource planning for the Palakkad district.