@article{KastiusSchlosser2022, author = {Kastius, Alexander and Schlosser, Rainer}, title = {Dynamic pricing under competition using reinforcement learning}, series = {Journal of revenue and pricing management}, volume = {21}, journal = {Journal of revenue and pricing management}, number = {1}, publisher = {Springer Nature Switzerland AG}, address = {Cham}, issn = {1476-6930}, doi = {10.1057/s41272-021-00285-3}, pages = {50 -- 63}, year = {2022}, abstract = {Dynamic pricing is considered a possibility to gain an advantage over competitors in modern online markets. The past advancements in Reinforcement Learning (RL) provided more capable algorithms that can be used to solve pricing problems. In this paper, we study the performance of Deep Q-Networks (DQN) and Soft Actor Critic (SAC) in different market models. We consider tractable duopoly settings, where optimal solutions derived by dynamic programming techniques can be used for verification, as well as oligopoly settings, which are usually intractable due to the curse of dimensionality. We find that both algorithms provide reasonable results, while SAC performs better than DQN. Moreover, we show that under certain conditions, RL algorithms can be forced into collusion by their competitors without direct communication.}, language = {en} } @article{RichlyBrauerSchlosser2020, author = {Richly, Keven and Brauer, Janos and Schlosser, Rainer}, title = {Predicting location probabilities of drivers to improved dispatch decisions of transportation network companies based on trajectory data}, series = {Proceedings of the 9th International Conference on Operations Research and Enterprise Systems - ICORES}, journal = {Proceedings of the 9th International Conference on Operations Research and Enterprise Systems - ICORES}, publisher = {Springer}, address = {Berlin}, pages = {12}, year = {2020}, abstract = {The demand for peer-to-peer ridesharing services increased over the last years rapidly. To cost-efficiently dispatch orders and communicate accurate pick-up times is challenging as the current location of each available driver is not exactly known since observed locations can be outdated for several seconds. The developed trajectory visualization tool enables transportation network companies to analyze dispatch processes and determine the causes of unexpected delays. As dispatching algorithms are based on the accuracy of arrival time predictions, we account for factors like noise, sample rate, technical and economic limitations as well as the duration of the entire process as they have an impact on the accuracy of spatio-temporal data. To improve dispatching strategies, we propose a prediction approach that provides a probability distribution for a driver's future locations based on patterns observed in past trajectories. We demonstrate the capabilities of our prediction results to ( i) avoid critical delays, (ii) to estimate waiting times with higher confidence, and (iii) to enable risk considerations in dispatching strategies.}, language = {en} } @article{KossmannHalfpapJankriftetal.2020, author = {Kossmann, Jan and Halfpap, Stefan and Jankrift, Marcel and Schlosser, Rainer}, title = {Magic mirror in my hand, which is the best in the land?}, series = {Proceedings of the VLDB Endowment}, volume = {13}, journal = {Proceedings of the VLDB Endowment}, number = {11}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3407790.3407832}, pages = {2382 -- 2395}, year = {2020}, abstract = {Indexes are essential for the efficient processing of database workloads. Proposed solutions for the relevant and challenging index selection problem range from metadata-based simple heuristics, over sophisticated multi-step algorithms, to approaches that yield optimal results. The main challenges are (i) to accurately determine the effect of an index on the workload cost while considering the interaction of indexes and (ii) a large number of possible combinations resulting from workloads containing many queries and massive schemata with possibly thousands of attributes.
In this work, we describe and analyze eight index selection algorithms that are based on different concepts and compare them along different dimensions, such as solution quality, runtime, multi-column support, solution granularity, and complexity. In particular, we analyze the solutions of the algorithms for the challenging analytical Join Order, TPC-H, and TPC-DS benchmarks. Afterward, we assess strengths and weaknesses, infer insights for index selection in general and each approach individually, before we give recommendations on when to use which approach.}, language = {en} } @article{Schlosser2020, author = {Schlosser, Rainer}, title = {Risk-sensitive control of Markov decision processes}, series = {Computers \& operations research : and their applications to problems of world concern}, volume = {123}, journal = {Computers \& operations research : and their applications to problems of world concern}, publisher = {Elsevier}, address = {Oxford}, issn = {0305-0548}, doi = {10.1016/j.cor.2020.104997}, pages = {14}, year = {2020}, abstract = {In many revenue management applications risk-averse decision-making is crucial. In dynamic settings, however, it is challenging to find the right balance between maximizing expected rewards and minimizing various kinds of risk. In existing approaches utility functions, chance constraints, or (conditional) value at risk considerations are used to influence the distribution of rewards in a preferred way. Nevertheless, common techniques are not flexible enough and typically numerically complex. In our model, we exploit the fact that a distribution is characterized by its mean and higher moments. We present a multi-valued dynamic programming heuristic to compute risk-sensitive feedback policies that are able to directly control the moments of future rewards. Our approach is based on recursive formulations of higher moments and does not require an extension of the state space. Finally, we propose a self-tuning algorithm, which allows to identify feedback policies that approximate predetermined (risk-sensitive) target distributions. We illustrate the effectiveness and the flexibility of our approach for different dynamic pricing scenarios. (C) 2020 Elsevier Ltd. All rights reserved.}, language = {en} } @article{SeiffertHolsteinSchlosseretal.2017, author = {Seiffert, Martin and Holstein, Flavio and Schlosser, Rainer and Schiller, Jochen}, title = {Next generation cooperative wearables}, series = {IEEE access : practical research, open solutions}, volume = {5}, journal = {IEEE access : practical research, open solutions}, publisher = {Institute of Electrical and Electronics Engineers}, address = {Piscataway}, issn = {2169-3536}, doi = {10.1109/ACCESS.2017.2749005}, pages = {16793 -- 16807}, year = {2017}, abstract = {Currently available wearables are usually based on a single sensor node with integrated capabilities for classifying different activities. The next generation of cooperative wearables could be able to identify not only activities, but also to evaluate them qualitatively using the data of several sensor nodes attached to the body, to provide detailed feedback for the improvement of the execution. Especially within the application domains of sports and health-care, such immediate feedback to the execution of body movements is crucial for (re-) learning and improving motor skills. To enable such systems for a broad range of activities, generalized approaches for human motion assessment within sensor networks are required. In this paper, we present a generalized trainable activity assessment chain (AAC) for the online assessment of periodic human activity within a wireless body area network. AAC evaluates the execution of separate movements of a prior trained activity on a fine-grained quality scale. We connect qualitative assessment with human knowledge by projecting the AAC on the hierarchical decomposition of motion performed by the human body as well as establishing the assessment on a kinematic evaluation of biomechanically distinct motion fragments. We evaluate AAC in a real-world setting and show that AAC successfully delimits the movements of correctly performed activity from faulty executions and provides detailed reasons for the activity assessment.}, language = {en} } @article{KossmannSchlosser2020, author = {Kossmann, Jan and Schlosser, Rainer}, title = {Self-driving database systems}, series = {Distributed and parallel databases}, volume = {38}, journal = {Distributed and parallel databases}, number = {4}, publisher = {Springer}, address = {Dordrecht}, issn = {0926-8782}, doi = {10.1007/s10619-020-07288-w}, pages = {795 -- 817}, year = {2020}, abstract = {Challenges for self-driving database systems, which tune their physical design and configuration autonomously, are manifold: Such systems have to anticipate future workloads, find robust configurations efficiently, and incorporate knowledge gained by previous actions into later decisions. We present a component-based framework for self-driving database systems that enables database integration and development of self-managing functionality with low overhead by relying on separation of concerns. By keeping the components of the framework reusable and exchangeable, experiments are simplified, which promotes further research in that area. Moreover, to optimize multiple mutually dependent features, e.g., index selection and compression configurations, we propose a linear programming (LP) based algorithm to derive an efficient tuning order automatically. Afterwards, we demonstrate the applicability and scalability of our approach with reproducible examples.}, language = {en} } @article{Schlosser2016, author = {Schlosser, Rainer}, title = {Stochastic dynamic pricing and advertising in isoelastic oligopoly models}, series = {European Journal of Operational Research}, volume = {259}, journal = {European Journal of Operational Research}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0377-2217}, doi = {10.1016/j.ejor.2016.11.021}, pages = {1144 -- 1155}, year = {2016}, abstract = {In this paper, we analyze stochastic dynamic pricing and advertising differential games in special oligopoly markets with constant price and advertising elasticity. We consider the sale of perishable as well as durable goods and include adoption effects in the demand. Based on a unique stochastic feedback Nash equilibrium, we derive closed-form solution formulas of the value functions and the optimal feedback policies of all competing firms. Efficient simulation techniques are used to evaluate optimally controlled sales processes over time. This way, the evolution of optimal controls as well as the firms' profit distributions are analyzed. Moreover, we are able to compare feedback solutions of the stochastic model with its deterministic counterpart. We show that the market power of the competing firms is exactly the same as in the deterministic version of the model. Further, we discover two fundamental effects that determine the relation between both models. First, the volatility in demand results in a decline of expected profits compared to the deterministic model. Second, we find that saturation effects in demand have an opposite character. We show that the second effect can be strong enough to either exactly balance or even overcompensate the first one. As a result we are able to identify cases in which feedback solutions of the deterministic model provide useful approximations of solutions of the stochastic model.}, language = {en} } @article{SchlosserRichly2019, author = {Schlosser, Rainer and Richly, Keven}, title = {Dynamic pricing under competition with data-driven price anticipations and endogenous reference price effects}, series = {Journal of revenue and pricing management}, volume = {18}, journal = {Journal of revenue and pricing management}, number = {6}, publisher = {Palgrave Macmillan}, address = {Basingstoke}, issn = {1476-6930}, doi = {10.1057/s41272-019-00206-5}, pages = {451 -- 464}, year = {2019}, abstract = {Online markets have become highly dynamic and competitive. Many sellers use automated data-driven strategies to estimate demand and to update prices frequently. Further, notification services offered by marketplaces allow to continuously track markets and to react to competitors' price adjustments instantaneously. To derive successful automated repricing strategies is challenging as competitors' strategies are typically not known. In this paper, we analyze automated repricing strategies with data-driven price anticipations under duopoly competition. In addition, we account for reference price effects in demand, which are affected by the price adjustments of both competitors. We show how to derive optimized self-adaptive pricing strategies that anticipate price reactions of the competitor and take the evolution of the reference price into account. We verify that the results of our adaptive learning strategy tend to optimal solutions, which can be derived for scenarios with full information. Finally, we analyze the case in which our learning strategy is played against itself. We find that our self-adaptive strategies can be used to approximate equilibria in mixed strategies.}, language = {en} } @article{SchlosserWaltherBoissieretal.2019, author = {Schlosser, Rainer and Walther, Carsten and Boissier, Martin and Uflacker, Matthias}, title = {Automated repricing and ordering strategies in competitive markets}, series = {AI communications : AICOM ; the European journal on artificial intelligence}, volume = {32}, journal = {AI communications : AICOM ; the European journal on artificial intelligence}, number = {1}, publisher = {IOS Press}, address = {Amsterdam}, issn = {0921-7126}, doi = {10.3233/AIC-180603}, pages = {15 -- 29}, year = {2019}, abstract = {Merchants on modern e-commerce platforms face a highly competitive environment. They compete against each other using automated dynamic pricing and ordering strategies. Successfully managing both inventory levels as well as offer prices is a challenging task as (i) demand is uncertain, (ii) competitors strategically interact, and (iii) optimized pricing and ordering decisions are mutually dependent. We show how to derive optimized data-driven pricing and ordering strategies which are based on demand learning techniques and efficient dynamic optimization models. We verify the superior performance of our self-adaptive strategies by comparing them to different rule-based as well as data-driven strategies in duopoly and oligopoly settings. Further, to study and to optimize joint dynamic ordering and pricing strategies on online marketplaces, we built an interactive simulation platform. To be both flexible and scalable, the platform has a microservice-based architecture and allows handling dozens of competing merchants and streams of consumers with configurable characteristics.}, language = {en} } @article{Schlosser2020, author = {Schlosser, Rainer}, title = {Scalable relaxation techniques to solve stochastic dynamic multi-product pricing problems with substitution effects}, series = {Journal of revenue and pricing management}, volume = {20}, journal = {Journal of revenue and pricing management}, number = {1}, publisher = {Palgrave Macmillan}, address = {Basingstoke}, issn = {1476-6930}, doi = {10.1057/s41272-020-00249-z}, pages = {54 -- 65}, year = {2020}, abstract = {In many businesses, firms are selling different types of products, which share mutual substitution effects in demand. To compute effective pricing strategies is challenging as the sales probabilities of each of a firm's products can also be affected by the prices of potential substitutes. In this paper, we analyze stochastic dynamic multi-product pricing models for the sale of perishable goods. To circumvent the limitations of time-consuming optimal solutions for highly complex models, we propose different relaxation techniques, which allow to reduce the size of critical model components, such as the state space, the action space, or the set of potential sales events. Our heuristics are able to decrease the size of those components by forming corresponding clusters and using subsets of representative elements. Using numerical examples, we verify that our heuristics make it possible to dramatically reduce the computation time while still obtaining close-to-optimal expected profits. Further, we show that our heuristics are (i) flexible, (ii) scalable, and (iii) can be arbitrarily combined in a mutually supportive way.}, language = {en} }