ScarceGAN: Discriminative Classification Framework for Rare Class Identification for Longitudinal Data with Weak Prior

This paper introduces ScarceGAN which focuses on identification of extremely rare or scarce samples from multi-dimensional longitudinal telemetry data with small and weak label prior. We specifically address: (i) severe scarcity in positive class, stemming from both underlying organic skew in the data, as well as extremely limited labels; (ii) multi-class nature of the negative samples, with uneven density distributions and partially overlapping feature distributions; and (iii) massively unlabelled data leading to tiny and weak prior on both positive and negative classes, and possibility of unseen or unknown behavior in the unlabelled set, especially in the negative class. Although related to PU learning problems, we contend that knowledge (or lack of it) on the negative class can be leveraged to learn the compliment of it (i.e., the positive class) better in a semi-supervised manner. To this effect, ScarceGAN re-formulates semi-supervised GAN by accommodating weakly labelled multi-class negative samples and the available positive samples. It relaxes the supervised discriminator's constraint on exact differentiation between negative samples by introducing a 'leeway' term for samples with noisy prior. We propose modifications to the cost objectives of discriminator, in supervised and unsupervised path as well as that of the generator. For identifying risky players in skill gaming, this formulation in whole gives us a recall of over 85% (~60% jump over vanilla semi-supervised GAN) on our scarce class with very minimal verbosity in the unknown space. Further ScarceGAN outperforms the recall benchmarks established by recent GAN based specialized models for the positive imbalanced class identification and establishes a new benchmark in identifying one of rare attack classes (0.09%) in the intrusion dataset from the KDDCUP99 challenge.

CognitionNet: A Collaborative Neural Network for Play Style Discovery in Online Skill Gaming Platform

Games are one of the safest source of realizing self-esteem and relaxation at the same time. An online gaming platform typically has massive data coming in, e.g., in-game actions, player moves, clickstreams, transactions etc. It is rather interesting, as something as simple as data on gaming moves can help create a psychological imprint of the user at that moment, based on her impulsive reactions and response to a situation in the game. Mining this knowledge can: (a) immediately help better explain observed and predicted player behavior; and (b) consequently propel deeper understanding towards players' experience, growth and protection. To this effect, we focus on discovery of the "game behaviours" as micro-patterns formed by continuous sequence of games and the persistent "play styles" of the players' as a sequence of such sequences on an online skill gaming platform for Rummy. We propose a two stage deep neural network, CognitionNet. The first stage focuses on mining game behaviours as cluster representations in a latent space while the second aggregates over these micro patterns to discover play styles via a supervised classification objective around player engagement. The dual objective allows CognitionNet to reveal several player psychology inspired decision making and tactics. To our knowledge, this is the first and one-of-its-kind research to fully automate the discovery of: (i) player psychology and game tactics from telemetry data; and (ii) relevant diagnostic explanations to players' engagement predictions. The collaborative training of the two networks with differential input dimensions is enabled using a novel formulation of "bridge loss". The network plays pivotal role in obtaining homogeneous and consistent play style definitions and significantly outperforms the SOTA baselines wherever applicable.

FAST-Q: Fast-track Exploration with Adversarially Balanced State Representations for Counterfactual Action Estimation in Offline Reinforcement Learning

Recent advancements in state-of-the-art (SOTA) offline reinforcement learning (RL) have primarily focused on addressing function approximation errors, which contribute to the overestimation of Q-values for out-of-distribution actions, a challenge that static datasets exacerbate. However, high stakes applications such as recommendation systems in online gaming, introduce further complexities due to player's psychology (intent) driven by gameplay experiences and the inherent volatility on the platform. These factors create highly sparse, partially overlapping state spaces across policies, further influenced by the experiment path selection logic which biases state spaces towards specific policies. Current SOTA methods constrain learning from such offline data by clipping known counterfactual actions as out-of-distribution due to poor generalization across unobserved states. Further aggravating conservative Q-learning and necessitating more online exploration. FAST-Q introduces a novel approach that (1) leverages Gradient Reversal Learning to construct balanced state representations, regularizing the policy-specific bias between the player's state and action thereby enabling counterfactual estimation; (2) supports offline counterfactual exploration in parallel with static data exploitation; and (3) proposes a Q-value decomposition strategy for multi-objective optimization, facilitating explainable recommendations over short and long-term objectives. These innovations demonstrate superiority of FAST-Q over prior SOTA approaches and demonstrates at least 0.15 percent increase in player returns, 2 percent improvement in lifetime value (LTV), 0.4 percent enhancement in the recommendation driven engagement, 2 percent improvement in the player's platform dwell time and an impressive 10 percent reduction in the costs associated with the recommendation, on our volatile gaming platform.