Refine
Document Type
- Article (16)
- Other (4)
- Conference Proceeding (1)
- Postprint (1)
Language
- English (22)
Is part of the Bibliography
- yes (22)
Keywords
- Dynamic pricing (3)
- heuristics (3)
- Competition (2)
- Dynamic pricing and advertising (2)
- Dynamic programming (2)
- E-commerce (2)
- Oligopoly competition (2)
- Peer-to-Peer ridesharing (2)
- dynamic (2)
- dynamic programming (2)
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.
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is challenging as the current location of each available driver is not exactly known since observed locations can be outdated for several seconds.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.
An efficient selection of indexes is indispensable for database performance. For large problem instances with hundreds of tables, existing approaches are not suitable: They either exhibit prohibitive runtimes or yield far from optimal index configurations by strongly limiting the set of index candidates or not handling index interaction explicitly. We introduce a novel recursive strategy that does not exclude index candidates in advance and effectively accounts for index interaction. Using large real-world workloads, we demonstrate the applicability of our approach. Further, we evaluate our solution end to end with a commercial database system using a reproducible setup. We show that our solutions are near-optimal for small index selection problems. For larger problems, our strategy outperforms state-of-the-art approaches in both scalability and solution quality.
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. <br /> 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.
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.
E-commerce marketplaces are highly dynamic with constant competition. While this competition is challenging for many merchants, it also provides plenty of opportunities, e.g., by allowing them to automatically adjust prices in order to react to changing market situations. For practitioners however, testing automated pricing strategies is time-consuming and potentially hazardously when done in production. Researchers, on the other side, struggle to study how pricing strategies interact under heavy competition. As a consequence, we built an open continuous time framework to simulate dynamic pricing competition called Price Wars. The microservice-based architecture provides a scalable platform for large competitions with dozens of merchants and a large random stream of consumers. Our platform stores each event in a distributed log. This allows to provide different performance measures enabling users to compare profit and revenue of various repricing strategies in real-time. For researchers, price trajectories are shown which ease evaluating mutual price reactions of competing strategies. Furthermore, merchants can access historical marketplace data and apply machine learning. By providing a set of customizable, artificial merchants, users can easily simulate both simple rule-based strategies as well as sophisticated data-driven strategies using demand learning to optimize their pricing strategies.
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.
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.
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.
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.