The digital environment is changing, leading to more complex and advanced cyber threats that require sophisticated cybersecurity measures. Decision support systems (DSS) are crucial for assisting cybersecurity professionals in making well-informed decisions to protect digital assets. This study presents a new hybrid method that combines a rule-based system with random forest to improve the accuracy and efficiency of cybersecurity decision-making by leveraging the advantages of both approaches. The proposed model combines the structured decision-making abilities of a rule-based system with the strong predictive capabilities of random forest, synergistically overcoming the limitations of each approach. The model aims to offer a more thorough and flexible solution to the ever-changing nature of cyber threats by combining these methodologies. The essence of the hybrid model is its capacity to analyze extensive datasets, identify patterns, and make precise decisions. Utilizing machine learning, particularly random forest, helps identify intricate relationships in data, allowing the system to adjust and develop in response to emerging threat vectors. The proposed model was validated using a varied dataset that included both identified cyber threats and harmless activities. The results show an impressive accuracy of 98.75%, highlighting the model’s effectiveness in accurately identifying threats. The false-positive rate (FPR) was determined to be 2.77%, indicating the model’s high precision and effectiveness in reducing false alarms. This research enhances cybersecurity systems by introducing a hybrid decision support model that combines rule-based systems and machine learning. The high accuracy and low false-positive rate shown highlight the potential of this approach to greatly improve cybersecurity decision-making, offering a valuable tool for professionals looking for effective and dependable threat detection methods in the constantly changing digital environment.