Procurement is an essential operation of every organization regardless of its size or domain. As such, aggregating the demands could lead to better value-for-money due to: (1) lower bulk prices; (2) larger vendor tendering; (3) lower shipping and handling fees; and (4) reduced legal and administration overheads. This paper describes our experience in developing an AI solution for demand aggregation and deploying it in A*STAR, a large governmental research organization in Singapore with procurement expenditure to the scale of hundreds of millions of dollars annually. We formulate the demand aggregation problem using a bipartite graph model depicting the relationship between procured items and target vendors, and show that identifying maximal edge bicliques within that graph would reveal potential demand aggregation patterns. We propose an unsupervised learning methodology for efficiently mining such bicliques using a novel Monte Carlo subspace clustering approach. Based on this, a proof-of-concept prototype was developed and tested with the end users during 2017, and later trialed and iteratively refined, before being rolled out in 2019. The final performance was 71% of past cases transformed into bulk tenders correctly detected by the engine; for new opportunities pointed out by the engine 81% were deemed useful for potential bulk tender contracts in the future. Additionally, per each valid pattern identified, the engine achieved 100% precision (all aggregated purchase orders were correct), and 79% recall (the engine correctly identified 79% of orders that should have been put into the bulk tenders). Overall, the cost savings from the true positive contracts spotted so far are estimated to be S$7 million annually.

Procurement is a set of activities and processes related to acquisition of goods and services through purchase orders placed by organization employees,from external contractors. Thisarticle describes practical experiments with procurement dataset of a major governmental organization in Singapore. In particular, we highlight the problems that emerge when trying to implement analytics for prediction of future purchases. The goal of such analytics is to deliver beneficial information to procurement office that plans and manages relationships with external sellers. In the article we describe the characteristics of the procurement dataset specifics and its implications on the future purchase problem that we attempt to solve using Markov chains model. Our analysis showshigh diversity of purchase descriptionsresulting in low ability to detect sequential patterns of purchasing officers. The solution presented in the article is additional dataset preprocessing involving use of hierarchical clustering. Our experiments with various similarity measures show an improvement allowing a practical deployment within our procurement analytics system prepared for the case study governmental organization.