Gracefully reducing the main memory footprint (e.g., via compression and data tiering) is an unsolved challenge for HTAP database systems, where most traditional reduction methods are no longer applicable. Since advantages of a reduced footprint are manyfold, the issue is of high importance for main memory-resident databases. In this paper, we present our work on Hyrise and discuss how we break down this challenge into three aspects in order to reduce the main memory consumption without losing the performance advantage of in-memory databases. First, we reduce existing allocations by efficiently selecting indices and workload-driven compression configurations for table data. Second, we use hybrid table layouts to tier data with minimal impacts on the runtime performance. Third, we employ data structures that efficiently eliminate unnecessary accesses to secondary storage. As an outlook, we depict our vision to eventually unite these aspects in a holistic footprint optimization.

Most sales applications are characterized by competition and limited demand information. For success- ful pricing strategies, frequent price adjustments as well as anticipation of market dynamics are crucial. Both effects are challenging as competitive markets are complex and computations of optimized pricing adjustments can be time-consuming. We analyze stochastic dynamic pricing models under oligopoly competition for the sale of perishable goods. To circumvent the curse of dimensionality, we propose a heuristic approach to efficiently compute price adjustments. To demonstrate our strategy’s applicability even if the number of competitors is large and their strategies are unknown, we consider different competitive settings in which competitors frequently and strategically adjust their prices. For all settings, we verify that our heuristic strategy yields promising results. We compare the performance of our heuristic against upper bounds, which are obtained by optimal strategies that take advantage of perfect price an- ticipations. We find that price adjustment frequencies can have a larger impact on expected profits than price anticipations. Finally, our approach has been applied on Amazon for the sale of used books. We have used a seller’s historical market data to calibrate our model. Sales results show that our data-driven strategy outperforms the rule-based strategy of an experienced seller by a profit increase of more than 20%.

Recent progress in machine learning and related fields like recommender systems open up new possibilities for data-driven approaches. One example is the prediction of a movie’s box office revenue, which is highly relevant for optimizing production and marketing. We use individual recommendations and user-based forecast models in a system that forecasts revenue and additionally provides actionable insights for industry professionals. In contrast to most existing models that completely neglect user preferences, our approach allows us to model the most important source for movie success: moviegoer taste and behavior. We divide the problem into three distinct stages: (i) we use matrix factorization recommenders to model each user’s taste, (ii) we then predict the individual consumption behavior, and (iii) eventually aggregate users to predict the box office result. We compare our approach to the current industry standard and show that the inclusion of user rating data reduces the error by a factor of 2x and outperforms recently published research.

Most online markets are characterized by competitive settings and limited demand information. Due to the complexity of such markets, efficient pricing strategies are hard to derive. We analyze stochastic dynamic pricing models in competitive markets with multiple offer dimensions, such as price, quality, and rating. In a first step, we use a simulated test market to study how sales probabilities are affected by specific customer behaviors and the strategic interaction of price reaction strategies. Further, we show how different state-of-the-art learning techniques can be used to estimate sales probabilities from partially observable market data. In a second step, we use a dynamic programming model to compute an effective pricing strategy which circumvents the curse of dimensionality. We demonstrate that the strategy is applicable even if the number of competitors is large and their strategies are unknown. We show that our heuristic can be tuned to smoothly balance profitability and speed of sales. Further, our approach is currently applied by a large seller on Amazon for the sale of used books. Sales results show that our data-driven strategy outperforms the rule-based strategy of an experienced seller by a profit increase of more than 20%.

Modern server systems with large NUMA architectures necessitate (i) data being distributed over the available computing nodes and (ii) NUMA-aware query processing to enable effective parallel processing in database systems. As these architectures incur significant latency and throughout penalties for accessing non-local data, queries should be executed as close as possible to the data. To further increase both performance and efficiency, data that is not relevant for the query result should be skipped as early as possible. One way to achieve this goal is horizontal partitioning to improve static partition pruning. As part of our ongoing work on workload-driven partitioning, we have implemented a recent approach called aggressive data skipping and extended it to handle both analytical as well as transactional access patterns. In this paper, we evaluate this approach with the workload and data of a production enterprise system of a Global 2000 company. The results show that over 80% of all tuples can be skipped in average while the resulting partitioning schemata are surprisingly stable over time.

Recent developments in database research intro- duced HTAP systems that are capable of handling both transactional and analytical workloads. These systems achieve their performance by storing the full data set in main memory. An open research question is how far one can reduce the main memory footprint without losing the performance superiority of main memory-resident databases. In this paper, we present a hybrid main memory-optimized database for mixed workloads that evicts cold data to less expensive storage tiers. It adapts the storage layout to mitigate the negative performance impact of secondary storage. A key challenge is to determine which data to place on which storage tier. We introduce a novel workload-driven model that determines Pareto-optimal allocations while also considering reallocation costs. We evaluate our concept for a production enterprise system as well as reproducible data sets.