cs.AISep 4, 2026

CHAMP: Cross-domain Hybrid Architecture for Matchmaking and Prediction in Online Multi-Player Games

Authors: Kai Wang, Ge Fan, Chaoyun Zhang, Yuyang Jiang, Yuze Liu

Organizations: Independent Researcher Santa Clara, United States · Independent Researcher Hangzhou, China · Independent Researcher Beijing, China · The Hong Kong University of Science and Technology Hong Kong SAR, China · 

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Multiplayer Online Battle Arena (MOBA) games rely on matchmaking to maintain competitive balance. Our prior work, CUPID, framed matchmaking as an assignment re-optimization problem and showed that a single-mode win-rate predictor can meaningfully rebalance teams. However, deploying such a system across diverse player populations exposes three practical bottlenecks: most queueing players lack sufficient in-mode match history (cold start), skill distributions shift drastically across rank tiers (distribution inconsistency), and extreme skill segments are severely data-starved. We present CHAMP, a cross-domain matchmaking framework that resolves these deployment bottlenecks. To address data sparsity and cold starts, CHAMP replaces the target-mode-only player profile with a hybrid domain feature collection: a timestamp-ordered cross-mode short-term sequence whose slices are annotated with target-domain features, plus per-mode breakdowns of long-term, real-time and team statistics. We further propose the Domain-Aware Win-rate Network (DAWN): a Domain-aware Knowledge Extractor (DAKE) compiles target-mode attributes into learnable representations that feed Domain-Aware Temporal/Spatial/Permutation OmniNet Encoders (DATOE/DASOE/DAPOE), so that mode-conditioned representations and per-mode debiasing are learned jointly inside a single shared network. Online, one trained DAWN serves every supported mode, with per-mode position-satisfaction thresholds as the only mode-specific knob. Offline, DAWN achieves 67.73% win-rate prediction accuracy, outperforming all evaluated attention and sequence baselines. Online A/B tests across the entire League ladder of a large-scale MOBA game, from novice players up to the top-expert players served by Elite Mode, demonstrate consistent drops in imbalanced matches. For lower-tier players, CHAMP reduces the 5-minute kill crushing rate by up to 20.73%.

Figures & tables

Figure 1. Overall architecture of CHAMP , extending Cupid with the Hybrid Domain Feature Collection, Dawn (DAKE + DATOE/DASOE/DAPOE)
ModelCasualLeagueElite
ACCRMSEACCRMSEACCRMSE
LR0.56570.49760.50400.50690.59120.4938
MLP0.57530.47710.51530.48660.60410.4725
LSTM0.59310.45820.52310.47010.63360.4514
Transformer0.60120.44120.54290.45180.65280.4316
OwO0.63210.42030.55650.43490.65590.4160
Table 1. Model comparison across three datasets (bold = best).
Figure 2. Ablation results on the Elite dataset.
ModeEconomy Crushing RateKill Crushing Rate
@5min@10min@15min@5min@15min
League Mode−- 2.14%−- 3.05%−- 3.45%−- 9.00%−- 8.05%
Elite Mode−- 3.32%−- 3.75%−- 3.84%−- 9.62%−- 8.19%
Table 2. Online A/B test results. Negative is better.
Rank TierEconomy Crushing RateKill Crushing Rate
@5min@10min@15min@5min@15min
Novice−- 4.98%−- 7.32%−- 8.15%−- 20.73%−- 16.45%
Junior−- 2.74%−- 3.70%−- 4.35%−- 12.74%−- 10.61%
Senior−- 1.99%−- 3.00%−- 3.59%−- 8.73%−- 8.76%
Expert−- 1.71%−- 2.32%−- 2.45%−- 6.30%−- 5.62%
Table 3. League Mode A/B results by skill tier.
More in this topic

Cross-Domain Transfer Learning

Cross-domain transfer learning reuses knowledge across datasets, populations, devices, or tasks when their distributions and feature spaces differ.

See all 206 papers

Explore similar work

CardsList
May 18, 2026

Robust Player-Conditional Champion Ranking for League of Legends: Style Similarity, Mastery Priors, and Archetype-Constrained Discovery

Champion recommendation in multiplayer online battle arena games is usually framed informally as a problem of metagame strength, personal comfort, or global win rate. We formalize champion recommendation in League of Legends as an interpretable, player-conditional ranking problem under sparse, noisy, and non-stationary behavioral data. The proposed framework combines four information sources: a population-strength proxy, player-style similarity, direct and indirect mastery priors, and archetype-level guardrails. The method uses robust median/MAD normalization, logarithmic transforms for skewed event counts, recency-weighted player style vectors, mastery-weighted champion-pool vectors, weighted cosine similarity, rank-scaled score components, and k-means++ clustering for coarse archetype support. The implemented prototype uses a Python/Pandas modeling layer, Supabase-backed storage, and a web-facing recommendation interface. Unlike black-box supervised win-prediction systems, the proposed method returns decomposed recommendation scores that can be inspected as expected-performance proxy, fit, mastery, and archetype compatibility. A single-player case study on a 100-game history for the player identifier DIVINERAINRACCON is included as an end-to-end sanity check. The manuscript is therefore a methods and systems contribution: it specifies a reproducible, modular, and auditable champion recommender and gives a validation protocol for future large-scale evaluation through temporal train-test splits, next-champion recovery, calibration analysis, and ablation studies.

Min Heo, Pranav Kadiyam, Prasun Panthi

Wabash College, Crawfordsville, IN 47933, USA · Arizona State University, Tempe, AZ 85281, USA

Learning to RankUser ModelingRecommender Systems
AskPDF
Jun 25, 2026

Computer Vision for MOBA Analytics: A Dataset and Baseline for Visibility Analysis in Dota 2

Introduction: Most Multiplayer Online Battle Arena (MOBA) analytics studies rely on structured data, which does not directly capture what each team could actually see during a match. Objective: This work introduces Dota2-Vis, a video-based dataset, and a baseline pipeline for visibility analysis in professional Dota 2 matches. Methodology: The dataset comprises all 144 matches from The International 2025, recorded from both team perspectives, totaling 288 Full HD videos, together with 2,477 manually annotated minimap images. We evaluate multiple variants of a modern object detector for player-icon detection and use the best-performing model to estimate opponent-visible player presence over time. Results: YOLO11l (large) achieved the best overall performance, reliably identifying player icons even in dense and visually cluttered minimap scenes. The resulting visibility curves reveal player, hero, role, and team-level patterns that complement conventional MOBA analytics, highlighting behavioral differences that are difficult to obtain from structured data alone. The Dota2-Vis dataset is publicly available at https://github.com/RicardoRCarvalho/dota2-vis/.

Ricardo da Rocha Carvalho, Eloísa Oliveira, Luiz Bernardo Martins Kummer +2

Pontifícia Universidade Católica do Paraná (PUCPR), Curitiba, Brasil

Sports Video Analysis
AskPDF
Oct 6, 2026

Learning in Dreams, Winning in Reality: A Continuous Dyna Loop for a Ten-Hero MOBA

World models are usually judged from the inside: by prediction loss, by the return a policy earns in imagination, or by how convincing their frames look. We judge one from the outside. We learn a structured, multi-agent world model of a complete ten-hero MOBA (206 units, every hero acting every tick, games of up to 6,000 ticks), train a policy only inside it with 1,400-tick free-running imagined episodes, and measure that policy in the real game against the opponent the game ships with. The real game never provides a gradient; it provides the policy's own games as training data for the world model, and an online evaluation that selects and anchors the policy. Run as a continuous asynchronous Dyna loop, the policy wins 70.2% of real games as radiant (421 of 600; 95% CI 66.4-73.7) on seeds never used for any decision, up from 0% for dream training alone and 33.7% before the loop. It wins none as dire, and neither does the shipped opponent when it plays itself. Four findings explain the result. Model exploitation is invisible from inside the dream: every unanchored run collapsed within a few updates while no in-dream metric tracked the collapse. A world model that is accurate on its training corpus is badly wrong on the policy's own games, and Dyna repairs it there, which is worth +9.2 points of real win rate with the policy recipe held fixed. Finally, the policy inherits its world model's fidelity profile mechanic by mechanic: the model represents the macro game but not crowd control, cast timing or lethality, and the policy wins by map-wide pressure with almost no coordinated fighting. We release the world model, the dream-PPO harness, a world-model debugger, the evaluation protocol, and every policy and log.

Jordy Kieto

Game-Playing AgentsModel-Based RLReinforcement LearningWorld Model LearningMulti-Agent Reinforcement LearningAction-Conditioned World Models
AskPDF