Automating Agency-Client Matching: Leveraging Recommender Systems for Efficient and Accurate Recommendations

Abstract

In today’s fast-paced and dynamic business landscape, optimizing operational processes is paramount. Agency-client matching is an important procedure that plays a critical role in aligning agencies with client needs for successful collaborations. Traditionally, this matching process required labour-intensive, manual evaluations of numerous agencies and their portfolios. However, the advent of advanced technologies and data-driven approaches has introduced recommender systems as valuable tools to streamline and automate this process. This study presents a unique and innovative cluster-based, hybrid filtering recommender system that utilizes machine learning algorithms and data analysis for agency-client matching. The recommender system follows a comprehensive three-step process, starting with brief preparation, then topic modelling and finally, agency ranking and scoring. Firstly, the briefs undergo a comprehensive pre-processing process to ensure inclusion of relevant text data by removing irrelevant information, such as stop words and entity names. Secondly, the filtered briefs go through topic modelling using the BERTopic framework to extract the keywords and underlying themes. Briefs are first transformed into numerical vectors using BERT embeddings, which helps to capture their semantic meaning and context. After that, dimensionality reduction is applied using UMAP to cluster related briefs. As a subsequent step, DBSTREAM is applied to assign new briefs to existing clusters, or create new clusters. The final step in this block is the implementation of c-TF-IDF which helps generate topic representations by identifying the most frequent words within each topic. Lastly, based on the unique cluster identifier assigned to the new brief, agencies are ranked and scored in line with the brief’s content and client requirements. All in all, the main focus of this study is to develop a ranking and scoring algorithm, tailored with certain criteria, to effectively shortlist relevant agency options and automate the agency-client matching process.