A government tender bidding system is a formal process where public sector projects are offered to private contractors through competitive bids. It ensures transparency, fairness, and cost-efficiency in awarding contracts for goods, services, or infrastructure development. Currently, research focuses on evaluating the processes, transparency, and efficiency of public procurement. A bidding system was developed that primarily focuses on automating and standardizing the evaluation of tender proposals. Researchers are currently exploring advanced prediction models, multi-criteria decision-making methods, data integration techniques, bias reduction strategies, and real-time evaluation systems to enhance the automation and fairness of government tender evaluations. The objective of this paper is to give a means of automating and improving the process for the evaluation of competitive government tender proposals. Decision support system will map various data inputs taken from diverse sources, including historical bid records, project specifications, and contractor profiles into one coherent database. In this paper, machine learning models such as Linear Regression, Extreme Gradient Boosting, and Technique for Order Preference by Similarity to Ideal Solution are used to predict the best bidder for the hosted tender and bids will be labeled in order to evaluate critical factors of experience of the bidder, cost, project timeline, and quality of the project. Operationally, the decision support system will revolutionize the efficiency of the tender evaluation process by standardizing the (time and frequency) assessments. This transparency plus creating awareness for profits will ensure that the correct and appropriate decisions are made in the tendering process. The outcome of the developed system is a more efficient, transparent, and data-driven evaluation process for government tenders, leading to optimal bidder selection and improved project success rates.