Heuristic Search in LegalTech: Dynamic Allocation of Legal Cases to Legal Staff

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


We investigate an allocation problem inspired by the process of assigning legal cases (matters) to staff in law firms. Addressing this problem is important as it can prevent issues around unbalanced workloads and over-recruitment, thus decreasing costs. This initial study on the topic frames the problem as a combinatorial dynamic single-objective problem (minimising tardiness) with constraints modelling staff-client relationships, staff capacities, and earliest start dates of matters. The paper motivates the allocation problem and puts it in context with the literature. Further contributions include: (i) a formal problem definition, (ii) the proposal and validation of a feature-rich problem generator to create realistic test cases, (iii) an initial analysis of the performance of selected heuristics (a greedy approach, a nature-inspired approach, and random search) on different test instances, and finally (iv) a discussion on directions for future research.
Original languageEnglish
Title of host publicationSixth International Conference on Machine Learning, Optimization, and Data Science (LOD)
Publication statusAccepted/In press - 25 Jun 2020


Dive into the research topics of 'Heuristic Search in LegalTech: Dynamic Allocation of Legal Cases to Legal Staff'. Together they form a unique fingerprint.

Cite this