Efficient Distance Pruning for Process Suffix Comparison in Prescriptive Process Monitoring

Prescriptive process monitoring seeks to recommend actions that improve process outcomes by analyzing possible continuations of ongoing cases. A key obstacle is the heavy computational cost of large-scale suffix comparisons, which grows rapidly with log size. We propose an efficient retrieval method exploiting the triangle inequality: distances to a set of optimized pivots define bounds that prune redundant comparisons. This substantially reduces runtime and is fully parallelizable. Crucially, pruning is exact: the retrieved suffixes are identical to those from exhaustive comparison, thereby preserving accuracy. These results show that metric-based pruning can accelerate suffix comparison and support scalable prescriptive systems.

💡 Research Summary

The paper addresses a fundamental scalability bottleneck in prescriptive process monitoring: the need to compare a large number of process suffixes in order to evaluate possible future continuations of ongoing cases and to recommend next‑best actions. Traditional exhaustive pairwise distance computation grows quadratically with the number of suffixes and quickly becomes infeasible for realistic event logs containing hundreds of thousands of cases.

To overcome this, the authors propose an exact pruning technique that leverages the triangle inequality of metric distance functions. A small set of “pivots” (P = {z_1, …, z_K}) is selected from the suffix space. For every suffix (x) the distances (d(x, z_k)) to all pivots are pre‑computed, yielding an (|S| \times K) distance matrix that can be reused across queries. When evaluating a pair ((x, y)), lower and upper bounds on the true distance are derived as

\