This study aims to develop a two-component data-mining decision support system (DM-DSS) to help consulting firms in the water industry make bid/no-bid decisions for international tenders.
To identify the key factors affecting bid decisions, a literature review was conducted along with expert consultations using the Delphi method and structured questionnaires. Five main criteria and 62 sub-criteria were prioritized. K-means clustering was used to categorize experts and assign weights to their opinions. A predictive model based on deep learning was developed and tested using real data from over 1,000 international tenders.
The final DM-DSS comprises two integrated components. The first component uses a deep learning model to predict the probability of winning a tender based on historical data. The second component involves a qualified expert committee, selected through clustering, to assess the desirability of each tender based on the identified criteria. The system provides a structured and time-efficient alternative to traditional manual approaches used by large consulting firms.
While most bid/no-bid studies focus on contractors, this research targets consultants in the water sector by developing a two-component DM-DSS that integrates data-driven prediction with structured expert judgement to support more informed and strategic tender participation.
