StratIncon Detector: Analyzing Strategy Inconsistencies Between Real-Time Strategy and Preferred Professional Strategy in MOBA Esports

TL;DR

MOBA esports hinge on balancing strategic preplanning with real-time execution, yet inconsistencies between real-time and preferred professional strategies can undermine performance and teamwork. The authors propose StratIncon Detector, a visual analytics system that processes Real-Time In-Game Information and Historical Match Performance, uses DETR for champion detection, Swin-Transformer for behavior classification, and LSTM to predict future strategy triads (champion, coordinates, behavior). The front-end provides Replay, Player Inconsistency, Team Performance, and Player Preference views to identify inconsistencies, quantify their impact on subsequent events, and reveal playstyle origins; validated through a case study, a 24-participant user study, and expert interviews, demonstrating improved insight, efficiency, and collaboration. The work offers actionable guidance for strategy analysis and team construction, and highlights potential for generalization to other MOBA titles and broader esports analytics.

Abstract

MOBA (Multiplayer Online Battle Arena) games require a delicate interplay of strategic planning and real-time decision-making, particularly in professional esports, where players exhibit varying levels of skill and strategic insight. While team strategies have been widely studied, analyzing inconsistencies in professional matches remains a significant challenge. The complexity lies in defining and quantifying the difference between real-time and preferred professional strategies, as well as understanding the disparities between them. Establishing direct causal links between specific strategic decisions and game outcomes also demands a comprehensive analysis of the entire match progression. To tackle these challenges, we present the StratIncon Detector, a visual analytics system designed to assist professional players and coaches in efficiently identifying strategic inconsistencies. The system detects real-time strategies, predicts preferred professional strategies, extracts relevant human factors, and uncovers their impact on subsequent game phases. Findings from a case study, a user study with 24 participants, and expert interviews suggest that, compared to traditional methods, the StratIncon Detector enables users to more comprehensively and efficiently identify inconsistencies, infer their causes, evaluate their effects on subsequent game outcomes, and gain deeper insights into team collaboration-ultimately enhancing future teamwork.

Figures (12)

• Figure 1: The StratIncon Detector pipeline includes: Data Processing for collecting and processing data, Back-end Engine for model training and strategy prediction, and Front-end Visualization for detecting inconsistencies and providing match insights.
• Figure 2: StratIncon Detector Back-end details: During strategy recognition, unlabelled match frames are processed by DETR to extract (1) champion categories and (2) coordinates. Resized champion slices are classified into (3) behavior categories using the Swin-Transformer. In the prediction phase, the previous five frames are input into LSTM to predict (4) the next frame's coordinates and behavior. Each player's Blood, Gold, Coordinates, and Behavior are encoded into a 9-dimensional vector per frame.
• Figure 3: All event icons for blue and red teams.
• Figure 4: StratIncon Detector Front-end Overview: (A) Replay View. (B) Player Inconsistency View. (C) Team Performance View. (D) Player Preference View.
• Figure 5: Overview of Replay View: (A1) Real-Time Gold Bar Plot.