How do people navigate the exploration-exploitation (EE) trade-off when making repeated choices with unknown rewards? We study this question through the lens of multi-armed bandit problems and introduce a novel behavioral model, Quantal Choice with Adaptive Reduction of Exploration (QCARE). It generalizes Thompson Sampling, allowing for a principled way to quantify the EE trade-off and reflect human decisionmaking patterns. The model adaptively reduces exploration as information accumulates, with the reduction rate serving as a parameter to quantify the EE trade-off dynamics. We theoretically analyze how varying reduction rates influence decision quality, shedding light on the effects of "over-exploration" and "under-exploration." Empirically, we validate QCARE through experiments collecting behavioral data from human participants. QCARE not only captures critical behavioral patterns in the EE trade-off but also outperforms alternative models in predictive power. Our analysis reveals a behavioral tendency toward over-exploration.

Given an sql, a rdbms performs a series of operations to generate a Query Execution Plan (qep), which tells how the results will be collected and returned eventually. The whole pipeline for obtaining the qep is the core functionality of a rdbms, thus is definitely a fundamental knowledge that must be acquired by database learners and junior engineers of any rdbms. Unfortunately, though the majority of rdbmss provide EXPLAIN statement to show the qep, general users cannot see how/why these plans are generated. The only way for learning that is to turn to the textbook, which contains limited number of predefined examples accordingly. However, they are too sketchy to allow us to have a hand-on experience in practice. In this work, we present a general framework, DBinsight, that unveils the query processing pipeline visually at each phase during the processing pipeline, including parsing, translating, query optimization, etc. Considering that the underlying designs and optimization strategies of rdbmss are different, in DBinsight we present an SQPProfile interface, such that heterogeneous data structures in various rdbmss are normalized to a uniform format. Thanks to that, in DBinsight we only need to focus on offering the presentation and interaction functionalities based on the uniformed SQPProfile, and do not need to worry about the difference in the underlying rdbmss.

We propose two recommendation algorithms for e-commerce with supply limits, a scenario that has not been intensively studied in the literature. One algorithm is a linear programming-based algorithm that uses historical data to approximate customer arrival patterns and generate shadow prices for inventories. The price of inventory can be introduced to existing recommendation algorithms to obtain adjusted rankings for recommendation. The other algorithm balances expected revenue and inventory consumption, and it uses a simple penalty function to reduce the chance of recommending low-inventory-level products. Both algorithms are suitable for online recommendation systems for grocery stores with both online and offline channels, and can incorporate the features of perishable products, which need to be sold within limited time. Both algorithms are tested in a simulation using estimated parameters from Freshippo, a supermarket owned by the Alibaba Group. The numerical results show that both algorithms can generate higher sales volume and higher revenue.