On-demand Food Research Articles

Crowdsourced on-demand food delivery: An order batching and assignment algorithm

Since the early 2010s, the meal delivery business went through a veritable revolution due to online food delivery platforms. By allowing customers to quickly order from a wide range of restaurants and outsourcing currently available couriers using their vehicles (crowdsourcing), this typology of service dynamically bridges demand and supply. The main goal of online food delivery platforms consists of matching couriers to meal orders within short time intervals to provide an efficient, reliable, and sustainable service. A way to increase efficiency consists of consolidating orders into batches, such that the same courier can serve several orders in multiple pickup and drop-off routes. Since such an assignment-batching problem becomes computationally prohibitively costly in real-world scenarios characterized by a large number of customer orders as well as uncertain demand and supply, heuristic solution methods come into play. This study proposes an order batching and assignment algorithm that leverages a graph-based approach after decomposing the original problem into more tractable sub-problems employing clustering. The solution is improved by local search moves and re-optimization procedures and integrated with advanced policies to improve solutions over time. An ‘Insertion policy’ aimed at increasing batch size, and a ‘Swap policy’ aimed at identifying more efficient assignments, are implemented and compared to a ‘Myopic policy’ that does not involve any re-optimization over time. An agent-based simulation framework is developed to implement dynamic policies where couriers’ operations and movements are realistically reproduced. The performance of the developed solution approach is tested through experiments based on a real-world case study. Results show that the algorithm allows for high-quality solutions in several configurations characterized by different demand and supply patterns (e.g., density levels, couriers availability) and problem sizes.In particular, the two advanced policies investigated considerably improve the solutions.

An economic analysis of on-demand food delivery platforms: Impacts of regulations and integration with ride-sourcing platforms

This paper presents an economic analysis of on-demand food-delivery platforms and investigates management strategies that protect restaurant owners and for-hire gig workers in the sharing economy. We consider two markets that are both operated based on sharing economy: (a) the food-delivery market where a platform offers on-demand food-delivery services to customers; and (b) the ride-sourcing market where a platform provides on-demand ride-hailing services to passengers. These two markets are interdependent as the two platforms share the same pool of for-hire drivers. An economic equilibrium model is proposed to capture the incentives of food-delivery customers, ride-hailing passengers, restaurant owners, for-hire drivers, the food-delivery platform, and the ride-sourcing platform. The profit-maximizing decisions of each platform are modeled, and both competitive and collaborative interactions between the platforms are characterized. Based on the model, we first investigate the impacts of a cap on the commission rate charged to restaurant owners. We find that within certain regime the commission cap would benefit restaurants. However, beyond this regime, the commission cap becomes overly-protective, and further reducing it will induce increased costs for food-delivery customers, reduced earnings for food-delivery couriers, reduced profits of the food-delivery platform, which can even lead to slightly reduced earnings for the restaurants, making everyone worse off in the food-delivery market (compared to a less aggressive commission cap). Furthermore, we consider an alternative strategy where no regulatory intervention is necessary and the food-delivery and ride-sourcing services are integrally operated by a single platform. We show that collaboration between the two platforms can offer a Pareto improvement when the market demand of the ride-sourcing service is relatively small.

Recommending-and-Grabbing: A Crowdsourcing-Based Order Allocation Pattern for On-Demand Food Delivery

With the development of intelligent transportation technologies, on-demand food delivery has become a prevalent logistics service that brings convenience to our daily life. However, problems such as inappropriate assignment and delayed delivery still exist in current food delivery platforms. To address these issues, this paper presents a Crowdsourced Recommending-and-Grabbing (CRG) system for order allocation in on-demand food delivery service. Unlike other traditional logistics systems, the CRG system considers the preferences of crowdsourced riders and allocates orders by recommending them to suitable crowdsourced riders. Riders can grab their favorite orders from personalized order lists. To optimize the experience of both customers and crowdsourced riders, a hierarchical solution framework composed of prediction and optimization is proposed to generate satisfactory order allocation schemes. First at the prediction part, we predict the preferences of crowdsourced riders by establishing a predictive model using eXtreme Gradient Boosting (XGBoost). Then at the optimization phase, an allocating-and-sequencing algorithm is designed to appropriately expose orders to crowdsourced riders and sequence the order list for each rider. Extensive experiments are conducted on real-world datasets and the comparative results demonstrate the effectiveness of the proposed methods, suggesting that the presented CRG system is promising to facilitate the on-demand food delivery effectively and efficiently.

The Impact of Consolidating On-Demand Food Delivery on Sustainability: A Simulation Study

Abstract On-demand food delivery services have transformed the food industry, offering customers a convenient way to order their favorite food from restaurants and have it delivered to their doorstep. However, the increased number of delivery vehicles has led to higher costs, traffic congestion, and carbon emissions. To tackle these negative impacts, consolidating the delivery process by combining multiple orders from different restaurants to various customers has been suggested. This study evaluates the sustainability impact of direct versus consolidated orders in the on-demand food delivery sector. To achieve the objective, we used an agent-based simulation model based on real delivery data from Yogyakarta, Indonesia. Our simulation results indicate that due to constraints in time windows and routing complexity, only a small portion of all orders can be consolidated. But where consolidation is feasible, it can benefit businesses and the environment by reducing costs for customers, increasing drivers’ productivity, and reducing carbon emissions. The downside is that it may result in a longer customer waiting time. These findings provide valuable insights for businesses and policymakers seeking to promote sustainable practices in the on-demand food delivery sector.

An Imitation Learning-Enhanced Iterated Matching Algorithm for On-Demand Food Delivery

As one representative of the emerging on-demand transport services, the on-demand food delivery (OFD) has penetrated into daily life. Due to its intrinsic complexities, the OFD has attracted the interest of a growing number of logistics researchers. This paper aims at optimizing the OFD process and addresses an OFD problem (OFDP). To overcome the dynamic and large-scale complexity, we abstract the OFDP into a static generalized assignment problem with a rolling horizon strategy. To meet the demand on high service quality and limited computation time, we propose an offline-optimization for online-operation framework based on imitation learning. Under this framework, an imitation learning-enhanced iterated matching algorithm (ILIMA) is proposed, which consists of three basic components: an iterated matching heuristic (IMH) to fast generate solutions, an expert to provide expertise, and a machine learning (ML) model to assist the decision-making process in IMH by mimicking the expert. In the offline-optimization phase, the ML model mines knowledge from the high-quality solutions optimized by the expert; in the online-operation phase, the IMH embedded with the well-trained ML model is deployed online to make decisions in a real OFD scenario. Offline simulation experiments are carried out on real historical data, which validate the superiority of ILIMA compared with existing methods. Moreover, rigorous online A/B tests are conducted on the scheduling system of Meituan, which demonstrates the practical value of ILIMA to improve customer satisfaction and delivery efficiency.

The High-Speed Digital Nomads Trapped in the System: Food Delivery Workers of Meituan

This article studies the temporality of platform labor through the specific lens of Meituan, the leading food delivery platform in China featuring an algorithm-driven dispatch system. This paper widens the existing research on platform labor from the perspective of time and speed. The on-demand food delivery service cultivates consumers’ expectations of timely satisfaction, nonetheless, it builds upon the rush, strictness, and flexibility of digital labor’s temporality which is often called a “mission impossible at times”. With the rhetoric of ‘Flexible work hours,’ the platform acts as an intermediary in the contradictory costumer-rider temporal relationship and prioritizes the customer's position within the temporal orders, where ICTs such as real-time tracking systems play a key role in sense-making. As the article will show, Meituan’s ETA (Estimated Time of Arrival) algorithm distributes the common interests of efficiency with the "invisible hand of value," in the quaternary relation between riders, customers, suppliers, and platform. While workers' time experience and negotiating ability are diminished, the platform gains the ultimate capacity to exploit platform labor systematically. The coordination of all platform algorithms normalizes class divisions and unequal power structures, interpreting the asymmetrical power between capital and labor in the platform economy.

Digital Work and Urban Delivery: Profile, Activity and Mobility Practices of On-Demand Food Delivery Couriers in Paris (France)

Platform-based on-demand delivery services are rapidly developing in urban areas, especially in the food sector, raising new issues for urban planners, especially in the field of transport. Based on a survey of over 100 couriers conducted in 2018 in the municipality of Paris (France), this work aims at analyzing the profile, delivery activity and mobility practices of the couriers working for these platforms. The main objective is to show how mobility practices are shaped by the characteristics of digital work in the urban delivery sector, and to highlight new challenges for urban authorities and research. Compared to other studies, our work is based on quantitative data and distinguishes three categories of couriers, depending on whether they have another activity: students, people with another paid job, and people with no other paid or non-paid activity. Findings show that these three categories have different characteristics, regarding age, education, residential location, the intensity of delivery activity and the characteristics of mobility practices, especially regarding the transport modes used. The article ends with the discussion of a number of new challenges for both urban authorities and researchers regarding the sustainability of these new forms of digital work in urban delivery.

Thermographic and rheological characterization of viscoelastic materials for hot-extrusion 3D food printing

Thermoreversible food materials are suitable for hot-extrusion 3D food printing (HE-3DFP) to customize food designs and enable on-demand food production. A challenge of HE-3DFP is to control the material phase transition such that it melts to allow flow and extrusion and rapidly solidifies afterwards to obtain stable printed structures. We here report on the use of thermal imaging to simultaneously monitor material cooling and deformation of common thermoreversible food materials during HE-3DFP. Thermographic and rheological measurements show that the structural deformation is driven by slow material cooling and prolonged printing time. The surface temperature of printed objects is a good indicator for structural stability. Solidification mechanisms such as cross-linking or strong particle jamming are required to prevent deformation in time (i.e. creep) during printing. Thus we recommend to set the printing temperature just above material's gelation temperature to ensure proper extrudability and structural stability of the printed foods.

From brick-and-mortar to location-less restaurant: The spatial fixing of on-demand food delivery platformization

Location has historically been vital to a restaurant's success. However, in the past decade, on-demand food delivery (ODFD) platforms like Meituan, Deliveroo, and Uber Eats have progressively increased their market shares, recently facilitated by the COVID-19 pandemic. Under the new circumstances, are restaurants still constrained by conventional locational factors, such as transport accessibility, customer proximity, and industrial agglomeration? How do ODFD platforms impact the geography of restaurants?This paper innovatively offers a comparative analysis of the different spatial distributions of brick-and-mortar and platform-dependent restaurants. Based on the case of Nanjing, China, robust empirical evidence demonstrates how platformization has spatially affected the catering sector. Using data from the most popular Chinese ODFD platform, Meituan, we analyze the following spatial characteristics of the catering sector in the urban core of Nanjing: transport accessibility, density pattern, agglomeration degree, and horizontal and vertical locational patterns. The findings suggest that platform-dependent restaurants have reduced dependence on transport accessibility. Compared with traditional brick-and-mortar restaurants, platform-dependent restaurants are more dispersed spatially, not only horizontally but also vertically. The digital turn in the catering sector is also noticeably associated with the rise of informal restaurants, such as ghost kitchens in vacant high-rise office spaces.

Modeling stochastic service time for complex on-demand food delivery

Uncertainty is everywhere in the food delivery process, which significantly influences decision-making for complex on-demand food delivery problems, affecting delivery efficiency and customer satisfaction. Especially, the service time is an indispensable part of the delivery process impacted by various uncertain factors. Due to the simplicity and high accuracy requirement, we model the uncertain service time as a Gaussian mixture model (GMM). In detail, we transform the distribution estimation problem into a clustering problem by determining the probability of each data belonging to each component (each cluster as well). A hybrid estimation of distribution algorithm is proposed to intelligently solve the clustering problem with the criterion to optimize quality and simplicity simultaneously. First, to optimize the simplicity, problem-specific encoding and decoding methods are designed. Second, to generate initial solutions with good clustering results, a Chinese restaurant process-based initialization mechanism is presented. Third, a weighted-learning mechanism is proposed to effectively guide the update of the probability model. Fourth, a local intensification based on maximum likelihood is used to exploit better solutions. The effect of critical parameters on the performances of the proposed algorithm is investigated by the Taguchi design of the experimental method. To demonstrate the effectiveness of the proposed algorithm, we carry out extensive offline experiments on real-world historical data. Besides, we employ the GMMs obtained by our algorithm in a real-world on-demand food delivery platform, Meituan, to assist decision-making for order dispatching. The results of rigorous online A/B tests verify the practical value of introducing the uncertainty model into the real-life application.

직무요구-자원 모델을 활용한 플랫폼 노동자의 일-여가갈등과 심리적웰빙에 관한 연구: 주문형 음식 배달원을 중심으로

The number of platform workers has increased rapidly due to the prolonged COVID-19 pandemic and the substantial growth of the platform industry. However, on-demand food couriers, who represent platform workers, particularly often experience a poor working environment. This study examined the relationships between their job demands, job resources, work-leisure conflict, and psychological well-being to improve their job environment and quality of life. Using a self-administered questionnaire, a total of 220 responses were collected among on-demand food couriers. According to the factor analysis, the sub-factors were derived for job demands(time pressure, professional isolation) and job resources(emotional support, informational support, customer value co-creation behavior) of on-demand food couriers. The results from the regression analyses indicated that job demands(time pressure, professional isolation) increased work-leisure conflict. And time pressure exacerbated psychological well-being, whereas professional isolation enhanced it. Emotional support and customer value co-creation behavior moderated the relationship between time pressure and work-leisure conflict, as well as the one between professional isolation and psychological well-being. This study offers implications to improve job and living conditions of on-demand food couriers.

Automated Hydroponic System using Wireless Sensor Networks

The exponential rise in population, the fall in fresh water table in many parts of the world, and the huge energy consumption and carbon footprint associated with the preservation and processing of food is a great threat (especially) to developing countries like Nigeria. Therefore, there is need for on-demand food production techniques that require minimum resources, such as; energy, fresh water, and plant nutrients. For these reasons scientists are now focusing their attention on hydroponics. Hydroponics is the process of growing crops without the use of soil. To ensure bumper harvest with minimum resources in hydroponics, di erent components of the system need to be closely and continuously monitored and controlled. In this paper, a wireless sensor networks technique for automating hydroponic systems is proposed. Simulation results shows that sensors and actuators can be deployed in a large scale hydroponic system with minimum resource use and minimum human intervention

Multi-method simulation approach: multiple restaurants to multiple customers on-demand food delivery services in Dubai

ABSTRACT Since early 2020, the COVID-19 outbreak has disrupted various supply chains including the on-demand food delivery sector. As a result, this service industry has witnessed a tremendous spike in demand that is affecting its delivery operations at the downstream level. Previous research studies have explored one-to-one and many-to-one solutions to the virtual food court delivery problem (VFCDP) to optimize on-demand food delivery services in different cities. However, research efforts have been limited to multiple restaurant orders from only one customer which does not apply to traditional systems where multiple customers request on-demand food delivery from multiple restaurants. This study rigorously analyses multiple restaurants to multiple customers (Many-to-many) food delivery simulation models in ideal weather conditions that are constrained with multiple key performance indicators (KPIs) such as delivery fleet utilization (the number of couriers utilized over the fleet size), average order delivery time, and fuel costs. This research also benchmarks the on-demand food delivery queueing methodologies using system dynamics and agent-based simulation modeling where three on-demand food delivery routing methodologies are simulated including First-in-First-Out (FIFO), Nearest, and Simulated Annealing using AnyLogic. The results suggest that the Many-to-many (Nearest) method outperforms other delivery routing methods which would have positive implications on optimizing existing food delivery systems and managerial decisions.

Towards alternative platform futures in post-pandemic cities? A case study on platformization and changing socio-spatial relations in on-demand food delivery

Digital platforms have become an increasingly central concept for reflecting societal processes, but the historical and spatial embeddedness of platformization is often neglected as dystopian warnings and promises of efficiency take center stage. The Covid-19 pandemic has further intensified discussion and speculation regarding the future of digital platforms and changing everyday routines in (post-)pandemic cities. Drawing on the case study of Graz (Austria), this paper expands generalized speculation by a concrete exploration of what alternative platform futures in (post-)pandemic cities might hold. The underlying aims are to identify case-specific socio-spatial dynamics with respect to the platformization of on-demand food delivery in Graz and to explore in what ways these dynamics were influenced by the pandemic.The article contextualizes the development of food delivery platforms in Europe, taking into consideration long-term enabling conditions such as neoliberal restructuring, financialization and the crisis of social reproduction, but also the boom of delivery platforms during the ‘lockdowns’ related to the Covid-19 pandemic. The case study draws on qualitative interviews with company officials, delivery workers, union representatives and restaurant owners to investigate the platforms' disruptive and unequal effects. Through this storying of the development of the platform economy for food deliveries in Graz from various perspectives in the pandemic city of the year 2020, the study challenges the narrative of a capital-driven and pervasive platformization. At the same time, the findings point out limitations of the local alternative platform model and contribute to the critical discourse on urban platforms.

KATN

Leveraging sensor data of mobile devices and wearables, activity detection is a critical task in various intelligent systems. Most recent work train deep models to improve the accuracy of recognizing specific human activities, which, however, rely on specially collected and accurately labeled sensor data. It is labor-intensive and time-consuming to collect and label large-scale sensor data that cover various people, mobile devices, and environments. In production scenarios, on the one hand, the lack of accurately labeled sensor data poses significant challenges to the detection of key activities; on the other hand, massive continuously generated sensor data attached with inexact information is severely underutilized. For example, in an on-demand food delivery system, detecting the key activity that the rider gets off his/her motorcycle to hand food over to the customer is essential for predicting the exact delivery time. Nevertheless, the system has only the raw sensor data and the clicking "finish delivery" events, which are highly relevant to the key activity but very inexact, since different riders may click "finish delivery" at any time in the last-mile delivery. Without exact labels of key activities, in this work, we propose a system, named KATN, to detect the exact regions of key activities based on inexact supervised learning. We design a novel siamese key activity attention network (SAN) to learn both discriminative and detailed sequential features of the key activity under the supervision of inexact labels. By interpreting the behaviors of SAN, an exact time estimation method is devised. We also provide a personal adaptation mechanism to cope with diverse habits of users. Extensive experiments on both public datasets and data from a real-world food delivery system testify the significant advantages of our design. Furthermore, based on KATN, we propose a novel user-friendly annotation mechanism to facilitate the annotation of large-scale sensor data for a wide range of applications.

Multi-Stove Scheduling for Sustainable On-Demand Food Delivery

Ordering food through mobile apps and crowdsourcing resources has become increasingly popular in the digital age. Restaurants can improve customer satisfaction to satisfy on-demand food orders by shortening waiting time and achieving sustainability through fuel reduction. In the present study, we construct a double-layer scheduling model, which is developed using the characteristics of on-demand food preparation, including the use of multiple stoves, a variety of dishes in one order, and the integration of the same dishes from different customers. The bottom layer is a multi-stove dish package scheduling model based on parallel machine scheduling. The upper layer is an order selection model based on the knapsack problem. To identify the optimal solution, four strategies for calculating the weight coefficient of the dish package are proposed to shorten the waiting time and realize sustainability. Numerical experiments are designed to analyze the differences of the final scheduling results under the four strategies. The bottom layer is extended to another model based on the vehicle routing optimization model, given the switch time between different dishes. The extension of the model is also compared in the numerical experiments. Our paper confirms the necessity of using a double-layer model for multi-strategy comparison in order to achieve sustainable on-demand scheduling.

Impacts of food accessibility and built environment on on-demand food delivery usage

On-demand food delivery (ODFD) services now produce many motorised trips in Chinese cities that raises environmental concerns. It is therefore crucial to understand where people use ODFD and what factors influence their usage. This paper explores the spatial patterns and determinants of ODFD usage in Shenzhen, China, focusing on the roles of food accessibility and the built environment. The results show that ODFD usage concentrates in more urbanised areas, especially city centres and sub-centres. Furthermore, more ODFD orders are generated in areas with lower food accessibility by walking and higher food accessibility by cycling, as well as in areas with higher population density, lower point of interest (POI) density, lower intersection density, higher street density, higher land use mix, higher percentage of land used for urban residences and commerce, and lower percentage of land used for rural residences, industries, and green space. These findings provide evidence-based implications for ODFD regulation.

Last-mile challenges in on-demand food delivery during COVID-19: understanding the riders' perspective using a grounded theory approach

PurposeThis paper aims to explore the last-mile (LM) challenges faced by on-demand food delivery (ODFD) riders during the coronavirus pandemic. This study contributes to the literature on the less-explored domain of ODFD services.Design/methodology/approachA grounded theory methodology is used. Riders working for multiple ODFD firms in various urban and semi-urban areas of India were interviewed. Open, axial and selective coding of interview transcripts was done.FindingsA grounded model is developed consisting of riders' challenges represented broadly under four core categories: Operational, Customer-related, Organisational and Technological issues. The study indicates that while some of the challenges are inherent to the ODFD supply chain, these have been visibly exposed and intensified by COVID-19, while other challenges are specific to the pandemic.Research limitations/implicationsThe model is a qualitative proposition representing LM delivery issues in ODFD services faced by the riders in India's urban and semi-urban areas during the COVID-19 pandemic. Other countries may face similar problems, but further studies are necessary to confirm or refute the findings.Practical implicationsODFD companies must address the riders' issues to better adapt to the current and future disruptions and improve riders' quality of work–life to achieve operational excellence.Originality/valueThis study builds on the extant ODFD literature by focusing on one of its less addressed aspects: the working conditions of the riders. This work is conducted amid the COVID-19 pandemic in the context of a developing country and aims to study the challenges in ODFD operations.

Odds stacked against workers: datafied gamification on Chinese and American food delivery platforms

AbstractThis article presents a cross-national comparative study examining how American and Chinese platform companies approach the gamification of on-demand food delivery. The study, based on ethnographic fieldwork in New York City and Beijing, shows how couriers in these cities negotiate the gamified app-based systems designed to convince them to log in and keep working. We argue that such systems are not only a salient form of ‘algorithmic management’—as has been argued before—but also demonstrate the central importance of datafication within the organizational strategies of food delivery companies operating under conditions of financialized platform capitalism. Indeed, the deeply financialized nature of the on-demand food delivery industry creates conditions in which companies experiment with data-driven gamification techniques in an effort to manipulate their flexible labor supply in an agile and cost-effective way—to thereby elicit higher productivity and meet expectations of investors and shareholders. Our comparative analysis challenges assumptions of a universal mode of gamification and highlights the differences between such situated techniques and their impacts on workers, identifying two distinct design approaches that we term ‘Deal or No Deal’ in New York and ‘Grab-and-Stack’ in Beijing.

On-demand food delivery: a systematic literature review

PurposeThe purpose of this paper is twofold: first, to review the extant academic literature on on-demand food delivery (ODFD) services, i.e. the delivery of freshly prepared meals from restaurants to customers enabled by online platforms; second, to propose directions for future research in this field.Design/methodology/approachThis work reviews 59 papers published between 2016 and 2020. They are classified with respect to both their research methodology and the addressed themes, namely the actors involved and the activities creating value for the ODFD ecosystem. The latter was analysed by applying a framework derived from the integration of traditional models and literature about platforms/business ecosystems. Results were validated through interviews with practitioners.FindingsDue to its huge success and the significant complexities behind it, the ODFD business has been gaining the interest of academics. The authors’ review highlights that (1) the perspectives of the various actors involved should be integrated, moving towards an ecosystem-based view; (2) future research should focus more on restaurant operations and their role in ODFD systems and (3) despite they have been investigated by several academic contributions, human resource management and logistics of ODFD systems still present room for further extensions, in the areas of intervention/regulation and distribution network/batching, respectively.Originality/valueThis review offers insights to both academics and practitioners. On the academic side, it analyses the literature on ODFD systems, outlining directions for future research. On the managerial side, it provides a comprehensive view on the most critical value-creating activities for ODFD businesses.