面向负责任游戏的不平滑多元时间序列的可解释与可解释性预测
Explainable and Interpretable Forecasts on Non-Smooth Multivariate Time Series for Responsible Gameplay
AI总结：
提出深度可操作预测网络（AFN），解决非平滑多元时间序列预测中的准确性、轨迹可解释性和特征解释三大挑战，在游戏过度沉迷预测中显著提升MSE并提前4周检测高风险玩家。
摘要：
多元时间序列（MTS）预测通过神经网络的最新进展（例如，Transformers）取得了长足进步（误差极小）。然而，在预测影响心理健康的游戏过度沉迷等关键情况下，没有贡献证据（解释）的准确预测是无关紧要的。因此，预测必须是可解释的——预测轨迹的中间表示是可理解的；同时必须是可解释的——注意力输入特征和事件是可访问的，以便对处于风险的玩家进行个性化和及时的干预。尽管目前关于可解释性的最先进研究主要关注时间平滑的单过程驱动时间序列数据，但我们的在线多人游戏数据由于玩家游戏结果与其进一步参与的意图之间的内在正交性，表现出难以处理的随机性。我们引入了一种新颖的深度可操作预测网络（AFN），它在一个单一解决方案中解决了与三个独立目标相关的相互依赖挑战：1）预测准确性；2）平滑可理解的轨迹；3）通过多维输入特征进行解释，同时应对由我们的非平滑时间数据引入的挑战。AFN通过以下方式建立了新的基准：（i）与基于SOM-VAE的SOTA网络相比，在玩家数据的预测MSE上实现了25%的改进；（ii）将玩家时间序列的不利进展归因于特定的未来时间步，前提是通过玩家特定的可操作输入特征消除近未来的过度沉迷玩家数量超过18%；（iii）平均提前4周主动检测出超过23%（比SOTA提升100%）的即将过度沉迷的玩家。
英文摘要：
Multi-variate Time Series (MTS) forecasting has made large strides (with very negligible errors) through recent advancements in neural networks, e.g., Transformers. However, in critical situations like predicting gaming overindulgence that affects one's mental well-being; an accurate forecast without a contributing evidence (explanation) is irrelevant. Hence, it becomes important that the forecasts are Interpretable - intermediate representation of the forecasted trajectory is comprehensible; as well as Explainable - attentive input features and events are accessible for a personalized and timely intervention of players at risk. While the contributing state of the art research on interpretability primarily focuses on temporally-smooth single-process driven time series data, our online multi-player gameplay data demonstrates intractable temporal randomness due to intrinsic orthogonality between player's game outcome and their intent to engage further. We introduce a novel deep Actionable Forecasting Network (AFN), which addresses the inter-dependent challenges associated with three exclusive objectives - 1) forecasting accuracy; 2) smooth comprehensible trajectory and 3) explanations via multi-dimensional input features while tackling the challenges introduced by our non-smooth temporal data, together in one single solution. AFN establishes a \it{new benchmark} via: (i) achieving 25% improvement on the MSE of the forecasts on player data in comparison to the SOM-VAE based SOTA networks; (ii) attributing unfavourable progression of a player's time series to a specific future time step(s), with the premise of eliminating near-future overindulgent player volume by over 18% with player specific actionable inputs feature(s) and (iii) proactively detecting over 23% (100% jump from SOTA) of the to-be overindulgent, players on an average, 4 weeks in advance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
