Identifying segments of interest: MOBA raw data are iteratively permuted by a certain amount of noise, which are then fed into a pre-trained ML model. With the classification score output by the model, we attain weights by measuring how much the original input’s classification score differs from that of the permuted samples, and finally weight time segments by averaging all matches of the same occurrence.


To ensure the playability of Multiplayer Online Battle Arena (MOBA) games, designers strive to balance different game occurrences. Although machine learning (ML) can help clas- sify matches into different occurrence categories, designers demand more flexible input, interpretable output, and inter- active collaboration with ML to facilitate analysis in breadth and depth. To this end, we work closely with a game com- pany to design a visual occurrence analytics system through a stepwise co-design process. We first identify bottlenecks in game designers’ conventional practices and their concerns about ML via an observational study. Then, we develop the single-match module of the visualization system to familiarize users with interactive analytics. Next, we incorporate ML models to recommend match segments of interest during oc- currence classification and streamline the cross-match analysis. Empirical studies confirm the efficacy of our system. Experts’ feedback suggests that our stepwise co-design process indeed helps them better embrace collaboration with machines.