Dynamic Pricing Algorithm Research Articles

Price Monitoring, or Where Surveillance Studies Meets the Sociology of Price Formation

This essay stages an encounter between surveillance studies and the sociology of price and price formation. I argue that surveillance is integral to the calculative operations of retail price strategies, especially during periods of high inflation, and that these calculative operations hinge on the human infrastructure of a precarious data-collecting workforce. I present my argument through a case study of competitor price monitoring, a corporate surveillance practice in which commercial actors record, process, and transmit information on competitors’ pricing, inventory, and display strategies. While pricing intelligence services like web-scraping and dynamic pricing algorithms are typically applied in e-commerce settings, I focus here on a firm that specializes in the collection of brick-and-mortar retail price data, with special attention to the labor practices involved in the manual (in-person, device-aided) production of retail price information at the national-industrial scale. Building on auto-ethnographic observations as a price data collector as well as analysis of employee reviews of the firm on sites like Indeed and Glassdoor, I argue that surveillance studies can contribute in significant ways to our understanding of the material practices, and politics, of price and price formation.

Commodity Dynamic Pricing and Replenishment Decision Model Based on Cosine Annealing

The purpose of this paper is to analyze the relationship between commodity sales volume, commodity types, sales time, etc., and propose a decision model to predict future sales data through historical sales data to determine a reasonable pricing strategy. First, the collected data is preprocessed. Through correlation analysis, the most important influencing factors of commodity sales are obtained. Through the construction of XGBoost model to model the influence factors obtained, the wholesale prices of chili products (yuan/kg) from July 1 to 7, 2023 are 3.63, 6.68, 6.90, 5.44, 6.62, 6.90, 5.44, respectively. In order to further develop a reasonable pricing strategy, this paper constructs a model based on cosine annealing algorithm combined with dynamic pricing algorithm. Through this model, it is calculated that from July 1 to 7, 2023, the restocking quantity (kg) of chili products is 234.20, 95.85, 110.04, 179.77, 176.60, 110.04, respectively. 179.77. Profit (Yuan) is 148.81, 298.96, 347.82, 370.75, 287.54, 356.33, 383.00. By comparing the model with the actual data, the error of the model is small and the robustness is high, which provides an effective decision-making model for supermarkets to formulate commodity sales strategy.

Optimisation and cross-validation of an e-hailing hybrid pricing algorithm using a supervised learning classification and regression tree model: a heuristic approach

Ride-hailing application price decisions are frequently considered biased and therefore are receiving more attention. Electronic (e)-hailing providers use the machine learning reinforcement model (RL) to build their dynamic pricing (DP) strategy to charge consumers. Nevertheless, the associated pricing issues in e-hailing potentially jeopardise this flourishing industry with a more significant long-term effect if left unresolved. Upon increased demand, the DP strategies assist the e-hailing systems with price surging, the unreasonable surging of price is unexpected by e-hailing users and deters them from using e-hailing services. A drawback of the existing RL DP algorithm is that does not consider surrounding factors before surging the price. Hence, this study aimed to address the underlying pricing issues through a hybrid pricing model using classification and regression tree (CART) supervised learning. A hybrid pricing algorithm was developed to demonstrate the enhanced model has edge over the existing model. The current e-hailing RL based algorithm was compared against the SL’s CART enhanced pricing algorithm with cross-validation using centrality analysis results. The test results shows that the hybrid pricing algorithm could address DP pricing issues by optimising e-hailing prices to provide its consumers with impartial pricing and remuneration. The proposed model can be a good theoretical reference for further studies which can also be applied to other industries such as Airlines, Tourism where DP is in used.

The technology impacts and AI solutions in hospitality

With the help of technology and Artificial Intelligence (AI), the hospitality industry has undergone a considerable change that has affected both the guest experience and the efficiency of operations. Through chatbots and virtual assistants, AIdriven solutions have become essential for improving interactions with guests, making personalized suggestions, and making reservations easier. Predictive analytics, Robotic Process Automation (RPA), and facial recognition technologies have made operations more efficient by improving security, finding the best pricing strategies, and automating routine tasks. Dynamic pricing algorithms look at market conditions and changes in demand in real-time, which has changed how revenue management is done. Contactless technologies, which AI has made simpler, are crucial to keeping things clean. AI-powered surveillance has strengthened safety and security measures. HR analytics and internal communication chatbots help managers streamline work processes and get employees more involved. IoT sensors make predictive maintenance possible, preventing equipment from breaking down by predicting when it needs maintenance. When voice recognition technology is built into a room, guests can use their voices to control amenities. Data analytics and Customer Relationship Management (CRM) systems also use AI to learn about guests' likes, dislikes, habits, and feedback, which helps with targeted marketing and providing more personalized services. Using secondary data, this study concluded that the hospitality industry continues to use AI and technology, and the sector moves forward thanks to the positive feedback loop between new ideas and happy customers. The study's findings show how AI solutions have changed hospitality, including making things better for guests, making things run more smoothly, and always trying to provide the best service possible.

Dynamic Demand-Aware Power Grid Intelligent Pricing Algorithm Based on Deep Reinforcement Learning

Dynamic Demand-Aware Power Grid Intelligent Pricing Algorithm Based on Deep Reinforcement Learning

Dynamic Pricing in Different Industries

Dynamic pricing describes a pricing strategy to set up highly flexible prices for products and services. Dynamic pricing algorithms adjust prices easily and frequently based on collected consumer data and market information. Dynamic pricing is used in various industries and has the potential to magnify revenues while offering multiple other benefits for companies. This paper analyzes the relevance and importance of dynamic pricing in sports, entertainment, leisure-time activities, hospitalities, and public transportation. For every industry, selected applications, and examples are analyzed. Finally, this paper investigates if dynamic pricing is fair and how customers respond to frequent price changes.

Dynamic Pricing with External Information and Inventory Constraint

A merchant dynamically sets prices in each time period when selling a product over a finite time horizon with a given initial inventory. The merchant utilizes new external information that is observed at the beginning of each time period, whereas the demand function—how the external information and the price jointly impact that single-period demand distribution—is unknown. The merchant’s decision, setting price dynamically, serves dual roles to learn the unknown demand function and to balance inventory with an ultimate objective to maximize the expected cumulative revenue. The main objective of this work is to characterize and provide a full spectrum of relations between the order of optimal expected cumulative revenue achieved in three decision-making regimes: the merchant’s online decision-making regime, a clairvoyant regime with complete knowledge about the demand function, and a deterministic regime in which all the uncertainties are relaxed to the expectations. In the analyses, we derive an unconstrained representation of the optimality gap for generic constrained online learning problems, which renders tractable lower and upper bounds for the expected revenue achieved by dynamic pricing algorithms between different regimes. This analytical framework also inspires the design of two dual-based dynamic pricing algorithms for the clairvoyant and online regimes. This paper was accepted by Hamid Nazerzadeh, data science. Supplemental Material: The online appendix and data are available at https://doi.org/10.1287/mnsc.2023.4963 .

Dynamic Pricing Provides Robust Equilibria in Stochastic Ridesharing Networks

Using prices induced by dual variables of a centralized optimization problem induces welfare-optimal equilibria among strategic drivers. We reveal a stark deficiency of such static pricing algorithms: it is possible for them to induce additional equilibria with arbitrarily low social welfare. Moreover, small perturbations to the marketplace, such as those caused by idiosyncratic randomness or model misspecification, can cause the welfare-optimal equilibrium to be Pareto-dominated (in terms of driver utility) by suboptimal equilibria. We show that dynamic pricing solves this problem. We describe a dynamic pricing algorithm that resolves the centralized optimization problem in each time period and show that it satisfies a new equilibrium robustness property, which guarantees that every induced (approximate) equilibrium is (approximately) welfare optimal. We also propose a novel two-level model of ridesharing networks with strategic drivers and spatiotemporal dynamics that lets us retain macroscopic uncertainty, such as correlated shocks caused by weather or other public events, when analyzing a large market limit in which idiosyncratic sources of uncertainty vanish. Funding: J. M. Cashore was supported by an NSERC PGS D Fellowship. P. Frazier was supported by AFOSR [Grant FA9550-19-1-0283]. É. Tardos was supported by AFOSR [Grant FA9550-19-1-0183] and [NSF Grants CCF-1408673 and CCF-1563714]. Supplemental Material: The online companion is available at https://doi.org/10.1287/moor.2022.0163 .

Distributed dynamic pricing of multiple perishable products using multi-agent reinforcement learning

Revenue management (RM) is essential for a wide range of industries such as airlines, hotels, cruise lines, fashion, and seasonal retail. This paper focuses on the multi-perishable-product dynamic pricing (MPPDP) problem, a significant research field in RM, where a company sells multiple interactive and perishable products over a limited selling window without replenishment. Most studies in this field assume customer behavior, which is modeled by demand function, is known in advance. Even when considering uncertainty in customer behavior, most studies still assume the mathematical form or structural properties of the underlying demand function are known in advance. However, these assumptions are usually inconsistent with the actual market situation. Recently, Reinforcement Learning (RL), a potent technique for handling sequential decision-making problems, has been increasingly applied to solve complex dynamic pricing problems without relying on any assumption about demand functions. However, the curse of dimensionality poses a challenge for currently used centralized RL algorithms when solving the MPPDP problem due to the exponential expansion of the joint price space with the number of products. To address this issue, our paper proposes a distributed dynamic pricing framework and innovatively models the MPPDP problem as a Fully Cooperative Markov Game solved by Multi-Agent Reinforcement Learning (MARL). Additionally, we use counterfactual baselines to design appropriate agent-specific reward signals that facilitate faster learning for the agents in our established multi-agent cooperative system. Finally, two MARL-based distributed dynamic pricing algorithms, Counterfactual Q-learning, and Counterfactual DQN, are proposed for the MPPDP problem. Through the case studies on four computer-simulated markets, we show that our algorithms can alleviate the curse of dimensionality faced by centralized RL algorithms, expedite the learning process, and demonstrate satisfactory performance without relying on any assumption about demand functions. In conclusion, our work provides an effective MARL-based distributed dynamic pricing framework and algorithms for companies to efficiently price their multiple perishable products in modern highly uncertain markets.

Examining sharing economy operations: A process perspective

<scp>Examining sharing economy operations</scp>: A <scp>process perspective</scp>

Differentially Private Demand Side Management for Incentivized Dynamic Pricing in Smart Grid

In order to efficiently provide demand side management (DSM) in smart grid, carrying out pricing on the basis of real-time energy usage is considered to be the most vital tool because it is directly linked with the finances associated with smart meters. Hence, every smart meter user wants to pay minimum possible amount along with getting maximum benefits. In here, usage based dynamic DSM pricing strategies plays their role and provide users with specific incentives. However, these reported real-time values can leak privacy of smart meter users, which can cause serious consequences such as spying. Moreover, most of dynamic pricing algorithms charge all users equally irrespective of their contribution in causing peak factor. Therefore, this paper proposes a modified usage based dynamic pricing mechanism that only charges the users responsible for causing peak factor. We further integrate differential privacy to protect the privacy of real-time smart metering data, and to calculate accurate billing we propose a noise adjustment method. Finally, we propose Demand Response enhancing Differential Pricing (DRDP) strategy that effectively enhances demand response along with providing dynamic pricing to smart meter users. The performance evaluation shows that DRDP outperforms previous mechanisms in terms of dynamic pricing and privacy preservation.

Ridesharing Price Prediction: Exploring the strategies of Dynamic Pricing

This paper explores the application of dynamic pricing algorithms in rideshare industries and examines the key variables that influence trip prices by analyzing Uber and Lyft Dataset of Boston in 2018. This dataset contains Uber and Lyft data mainly from November and December 2018. It contains essential variables such like distance and price for rideshare price prediction, together with many other variables which could be included in regression model such as weather and hours in the day. The Ordinary Least Square regression method is used in this paper, and results shows that the most influential and statistically significant variables on price are the distance of trip and surge multiplier which indicates traffic surge. The regression result is in accordance with the intuition that price is positively correlated with distance and price goes up during surge time. The result implies that the dynamic pricing algorithm that adjusts live prices heavily relies on the current traffic condition and distance of the trip, while the price is not determined by hour of the trip during the day and temperature.

Dynamic Pricing and Placing for Distributed Machine Learning Jobs: An Online Learning Approach

Nowadays distributed machine learning (ML) jobs usually adopt a parameter server (PS) framework to train models over large-scale datasets. Such ML job deploys hundreds of concurrent workers, and model parameter updates are exchanged frequently between workers and PSs. Current practice is that workers and PSs may be placed on different physical servers, bringing uncertainty in jobs’ runtime. Existing cloud pricing policy often charges a fixed price according to the job’s runtime. Although this pricing strategy is simple to implement, such pricing mechanism is not suitable for distributed ML jobs whose runtime is stochastic and can only be estimated according to its placement after job admission. To supplement existing cloud pricing schemes, we design a dynamic pricing and placement algorithm, DPS, for distributed ML jobs. DPS aims to maximize the cloud service provider’s profit, which dynamically calculates unit resource price upon a job’s arrival, and determines job’s placement to minimize its runtime if offered price is accepted to users. Our design exploits the multi-armed bandit (MAB) technique to learn unknown information based on past sales. DPS balances the exploration and exploitation stage, and selects the best price based on the reward which is related to job runtime. Our learning-based algorithm can increase the provider’s profit by 200%, and achieves a sub-linear regret with both the time horizon and the total job number, compared to benchmark pricing schemes. Extensive evaluations using real-world data also validates the efficacy of DPS.

Blockchain-Based Resource Trading in Multi-UAV-Assisted Industrial IoT Networks: A Multi-Agent DRL Approach

With the Industrial Internet of Things (IIoT), mobile devices (MDs) and their demands for low-latency data communication are increasing. Due to the limited resources of MDs, such as energy, computation, storage, and bandwidth, IIoT systems cannot meet MDs’ quality of service (QoS) and security requirements. Recently, UAVs have been deployed as aerial base stations in the IIoT network to provide connectivity and share resources with MDs. We consider a resource trading environment where multiple resource providers compete to sell their resources to MDs and maximize their profit by continually adjusting their pricing strategies. Multiple MDs, on the other hand, interact with the environment to make purchasing decisions based on the prices set by resource providers to reduce costs and improve QoS. We propose a novel intelligent resource trading framework that integrates multi-agent deep reinforcement Learning (MADRL), blockchain, and game theory to manage dynamic resource trading environments. A consortium blockchain with a smart contract is deployed to ensure the security and privacy of the resource transactions. We formulated the optimization problem using a Stackelberg game. However, the formulated optimization problem in the multi-agent IIoT environment is complex and dynamic, making it difficult to solve directly. Thus, we transform it into a stochastic game to solve the dynamics of the optimization problem. We propose a dynamic pricing algorithm that combines the Stackelberg game with the MADRL algorithm to solve the formulated stochastic game. The simulation results show that our proposed scheme outperforms others to improve resource trading in UAV-assisted IIoT networks.

Context‐based dynamic pricing with online clustering

We consider a context‐based dynamic pricing problem of online products, which have low sales. Sales data from Alibaba, a major global online retailer, illustrate the prevalence of low‐sale products. For these products, existing single‐product dynamic pricing algorithms do not work well due to insufficient data samples. To address this challenge, we propose pricing policies that concurrently perform clustering over product demand and set individual pricing decisions on the fly. By clustering data and identifying products that have similar demand patterns, we utilize sales data from products within the same cluster to improve demand estimation for better pricing decisions. We evaluate the algorithms using regret, and the result shows that when product demand functions come from multiple clusters, our algorithms significantly outperform traditional single‐product pricing policies. Numerical experiments using a real data set from Alibaba demonstrate that the proposed policies, compared with several benchmark policies, increase the revenue. The results show that online clustering is an effective approach to tackling dynamic pricing problems associated with low‐sale products.

Dynamic air ticket pricing using reinforcement learning method

This paper studies a dynamic air ticket pricing problem in a strategic and myopic passengers co-existence market. The strategic or myopic passengers can be further divided into high-valuation and low-valuation groups according to how they evaluate their purchases. The strategic passengers have different strategic levels. When the airline sets a ticket price, every passenger makes his or her purchase decision according to his or her type and the strategic level, or might select “wait” or “leave (the market)”. The paper firstly proposes a dynamic pricing algorithm in which the utilities of both the airline and passengers are considered. The reinforcement learning (RL) is employed to deal with the progressive or dynamic decision-making framework, in which the dynamic pricing problem is formulated as a discrete finite Markov decision process (MDP) and the Q-learning is adopted to solve the problem. By using this method, the airline can adaptively decide the ticket price based on passengers strategic behaviors and the time-varying demand. The effects of the passenger type proportion and strategic level are analyzed. The computational results show the higher proportion of strategic passengers is, the smaller price increase the airline can adopt, and the higher proportion of high-valuation strategic passengers is, the larger price increase the airline can put to use under the same strategic level. If the proportion of low-valuation strategic passengers is higher, the price increase should be gentle and step by step when the price increase strategy is adopted. If the airline uses price-cut policy, the adjustment should be small. In addition, the high-valuation passenger mainly affects high-price periods and the low-valuation passenger mainly affects low-price periods. When the proportion of strategic passengers is fixed, the lower the passenger strategic level is, the larger the price slope is. These findings can provide some references for the airline to make more precise and flexible pricing decisions.

General dynamic pricing algorithms based on universal exponential booking curves

General dynamic pricing algorithms based on universal exponential booking curves

Meta Dynamic Pricing: Transfer Learning Across Experiments

We study the problem of learning shared structure across a sequence of dynamic pricing experiments for related products. We consider a practical formulation in which the unknown demand parameters for each product come from an unknown distribution (prior) that is shared across products. We then propose a meta dynamic pricing algorithm that learns this prior online while solving a sequence of Thompson sampling pricing experiments (each with horizon T) for N different products. Our algorithm addresses two challenges: (i) balancing the need to learn the prior (meta-exploration) with the need to leverage the estimated prior to achieve good performance (meta-exploitation) and (ii) accounting for uncertainty in the estimated prior by appropriately “widening” the estimated prior as a function of its estimation error. We introduce a novel prior alignment technique to analyze the regret of Thompson sampling with a misspecified prior, which may be of independent interest. Unlike prior-independent approaches, our algorithm’s meta regret grows sublinearly in N, demonstrating that the price of an unknown prior in Thompson sampling can be negligible in experiment-rich environments (large N). Numerical experiments on synthetic and real auto loan data demonstrate that our algorithm significantly speeds up learning compared with prior-independent algorithms. This paper was accepted by George J. Shanthikumar, Management Science Special Section on Data-Driven Prescriptive Analytics.

Impact of Accurate Detection of Freeway Traffic Conditions on the Dynamic Pricing: A Case Study of I-95 Express Lanes.

Express lanes (ELs) implementation is a proven strategy to deal with freeway traffic congestion. Dynamic toll pricing schemes effectively achieve reliable travel time on ELs. The primary inputs for the typical dynamic pricing algorithms are vehicular volumes and speeds derived from the data collected by sensors installed along the ELs. Thus, the operation of dynamic pricing critically depends on the accuracy of data collected by such traffic sensors. However, no previous research has been conducted to explicitly investigate the impact of sensor failures and erroneous sensors’ data on toll computations. This research fills this gap by examining the effects of sensor failure and faulty detection scenarios on ELs tolls calculated by a dynamic pricing algorithm. The paper’s methodology relies on applying the dynamic toll pricing algorithm implemented in the field and utilizing the fundamental speed-volume relationship to ‘simulate’ the sensors’ reported data. We implemented the methodology in a case study of ELs on Interstate-95 in Southeast Florida. The results have shown that the tolls increase when sensors erroneously report higher than actual traffic demand. Moreover, it has been found that the accuracy of individual sensors and the number of sensors utilized to estimate traffic conditions are critical for accurate toll calculations.

Energy trading and control of islanded DC microgrid using multi-agent systems

The energy sector is experiencing a revolution that is fuelled by a multitude of factors. Among them are the aging grid system, the need for cleaner energy and the increasing demands on energy sector. The demand-response program is an advanced feature in smart grid that strives to match suppliers to their demands using price-based and incentive programs. The objective of the work is to analyse the performance of the load shedding technique using dynamic pricing algorithm. The system was designed using multi-agent system (MAS) for a DC microgrid capable of real-time monitoring and controlling of power using price-based demand-response program. As a proof of concept, the system was implemented using intelligent physical agents, Java Agent Development Framework (JADE), and agent simulation platform (REPAST) with two residential houses (non-critical loads) and one hospital (critical load). The architecture has been implemented using embedded devices, relays, and sensors to control the operations of load shedding and energy trading in residential areas that have no access to electricity. The measured results show that the system can shed the load with the latency of less than 600 ms, and energy cost saving with an individual houses by 80% of the total cost with 2USD per day. The outcome of the studies demonstrates the effectiveness of the proposed multi-agent approach for real-time operation of a microgrid and the implementation of demand-response program.