In insight recommendation systems, obtaining timely and high-quality recommended visual analytics over incomplete data is challenging due to the difficulties in cleaning and processing such data. Failing to address data incompleteness results in diminished recommendation quality, compelling users to impute the incomplete data to a cleaned version through a costly imputation strategy. This paper introduces VizPut scheme, an insight-aware selective imputation technique capable of determining which missing values should be imputed in incomplete data to optimize the effectiveness of recommended visualizations within a specified imputation budget. The VizPut scheme determines the optimal allocation of imputation operations with the objective of achieving maximal effectiveness in recommended visual analytics. We evaluate this approach using real-world datasets, and our experimental results demonstrate that VizPut effectively maximizes the efficacy of recommended visualizations within the user-defined imputation budget.

翻译：在洞察推荐系统中，由于不完整数据的清洗与处理存在困难，难以获得及时且高质量的推荐可视化分析。若未能解决数据不完整问题，推荐质量将显著降低，迫使用户通过高成本的插补策略将不完整数据转化为清洁版本。本文提出VizPut方案——一种具有洞察感知能力的选择性插补技术，能够在指定插补预算内，确定不完整数据中哪些缺失值应被插补，从而优化推荐可视化的有效性。VizPut方案以最大化推荐可视化分析效果为目标，确定插补操作的最优分配。我们使用真实数据集对该方法进行评估，实验结果表明，VizPut能在用户定义的插补预算内有效最大化推荐可视化的效果。