Driver Income Research Articles

Platform integration in ride-sourcing markets with heterogeneous passengers

This paper explores the impacts of a novel business model termed platform integration, which enables passengers to simultaneously request on-demand rides from multiple ride-sourcing platforms via a third-party integrator. In particular, we employ an equilibrium model where passenger demand and driver supply are endogenously dependent on the prices and wages that emerge from the competitive interaction between two platforms, with and without an integrator. A Hotelling model is adopted to characterize passengers’ heterogeneity in service preference for different platforms. We employ the concepts of a Nash equilibrium and a shared monopoly to analyze equilibrium outcomes that can arise in various settings of demand and supply characteristics with and without platform integration. We find that how the platform should adjust its price and wage at Nash equilibrium as potential demand increases is affected by the nature of supply. We also find that the profit at Nash equilibrium can increase or decrease in supply capacity depending on the competitive situation of the platforms. We build on these equilibrium results to analyze how platform integration affects the platform’s decision-making of price and wage, and market performance. We find that platform integration can increase platform profit but reduce driver income, and may hurt passengers who have a strong preference for one certain platform, especially in the case of a less heterogeneous supply.

Pekerja Ekonomi Gig: Pengalaman Kerja Pengemudi Ojek Online Maxim dan Grab di Wilayah Timur Indonesia

This study aims to examine the work experience of online Ojek drivers in Kupang City who use the Maxim and Grab platforms. This research is motivated by the rapid development of online ojek services in Indonesia, including in Kupang City, as well as its important role in providing new economic opportunities. This research uses a qualitative approach with phenomenological methods to explore the subjective experiences of the drivers. In-depth interview techniques and participatory observation were used to collect data from 22 informants consisting of Maxim and Grab drivers. The results showed significant differences between the drivers' work experiences on the two platforms. Grab drivers prefer the strict Standard Operating Procedures (SOPs) that provide a sense of security, while Maxim drivers appreciate the flexibility of working hours offered. The main challenges faced by drivers include digital map inaccuracies, sudden order cancellations, accident risks, and poor road conditions. The rating system plays an important role in determining a driver's income, with high ratings increasing the number of orders. This research makes an important contribution to the literature by providing an in-depth comparative analysis of the work experience of online ojek drivers in a medium-sized city like Kupang. The findings also offer practical recommendations for online Ojek companies to improve driver welfare and provide useful data for policymakers in formulating regulations that support the welfare of online Ojek drivers.

Klasifikasi Pendapatan Driver Shopee Food Menggunakan Metode K-Means

PT Shopee Internasional Indonesia is a company that has e-commerce features and also has a food and food delivery service known as Shopee Food which started operating in April 2020. At the beginning of 2021, Shopee Food started fulfilling food and drink orders, thereby attracting many driver partners to deliver it to consumers. This is because the payment system is easy to use. The income received by drivers through ShopeePay is accumulated and properly recorded in the Shopee Food driver account. Therefore, it is necessary to classify a driver's income every week to find out the highest and lowest income. The aim of the research carried out is grouping to minimize the objective function set in the clustering process, which basically tries to minimize variation within one cluster and maximize variation between clusters, and to classify several incomes based on the K-Means method. The research method used is the K-Means clustering method which is used to group data into several groups (clusters) based on similar features. Data collection was carried out for 5 months (May-October) 2023. Then the data obtained was identified in which week the income data was the highest and lowest. So the clustering is carried out which is displayed in the diagram by marking 4 features to make it easier to read the results, namely red (low), blue (medium), black (highest), and blue box (average). The results obtained based on diagrams (visual data) produce the highest data in the 1st month with income of IDR 39,000.00, while the lowest data is in the 4th month with IDR 6,400.00 and with a small data ratio. The conclusion obtained from the research results is that you get the highest income, namely in month 1 with an income of IDR 39,000.00.

I-Rebalance: Personalized Vehicle Repositioning for Supply Demand Balance

Ride-hailing platforms have been facing the challenge of balancing demand and supply. Existing vehicle reposition techniques often treat drivers as homogeneous agents and relocate them deterministically, assuming compliance with the reposition. In this paper, we consider a more realistic and driver-centric scenario where drivers have unique cruising preferences and can decide whether to take the recommendation or not on their own. We propose i-Rebalance, a personalized vehicle reposition technique with deep reinforcement learning (DRL). i-Rebalance estimates drivers' decisions on accepting reposition recommendations through an on-field user study involving 99 real drivers. To optimize supply-demand balance and enhance preference satisfaction simultaneously, i-Rebalance has a sequential reposition strategy with dual DRL agents: Grid Agent to determine the reposition order of idle vehicles, and Vehicle Agent to provide personalized recommendations to each vehicle in the pre-defined order. This sequential learning strategy facilitates more effective policy training within a smaller action space compared to traditional joint-action methods. Evaluation of real-world trajectory data shows that i-Rebalance improves driver acceptance rate by 38.07% and total driver income by 9.97%.

Fairness-Aware Dynamic Ride-Hailing Matching Based on Reinforcement Learning

The core issue in ridesharing is designing reasonable algorithms to match drivers and passengers. The ridesharing matching problem, influenced by various constraints such as weather, traffic, and supply–demand dynamics in real-world scenarios, requires optimization of multiple objectives like total platform revenue and passenger waiting time. Due to its complexity in terms of constraints and optimization goals, the ridesharing matching problem becomes a central issue in the field of mobile transportation. However, the existing research lacks exploration into the fairness of driver income, and some algorithms are not practically applicable in the industrial context. To address these shortcomings, we have developed a fairness-oriented dynamic matching algorithm for ridesharing, effectively optimizing overall platform efficiency (expected total driver income) and income fairness among drivers (entropy of weighted amortization fairness information between drivers). Firstly, we introduced a temporal dependency of matching outcomes on subsequent matches in the scenario setup and used reinforcement learning to predict these temporal dependencies, overcoming the limitation of traditional matching algorithms that rely solely on historical data and current circumstances for order allocation. Then, we implemented a series of optimization solutions, including the introduction of a time window matching model, pruning operations, and metric representation adjustments, to enhance the algorithm’s adaptability and scalability for large datasets. These solutions also ensure the algorithm’s efficiency. Finally, experiments conducted on real datasets demonstrate that our fairness-oriented algorithm based on reinforcement learning achieves improvements of 81.4%, 28.5%, and 79.7% over traditional algorithms in terms of fairness, platform utility, and matching efficiency, respectively.

The trend of the structural change of the city taxi market in China: a modal split analysis in the context of different market access rules

ABSTRACT To elucidate the impact of online car-hailing (OCH) on traditional taxi services and in producing structural changes to urban taxi markets in China, we propose a model based on the market access rules and business models of the two modes that analyzes their interactions in the following arenas: fleet size, passenger waiting time, service level, and driver income. Then, we build a nested logit model to predict the modal splits and market shares for four travel modes (online car-hailing, traditional taxi, metro, and bus). Taking Ningbo as an example, we estimate the changes in the number of OCH vehicles, the modal splits of the four travel modes, and the new equilibrium in urban taxi service markets. We show that OCH puts significant pressure on the traditional taxi market due to the positive feedback between OCH fleet size and its service quality.

Freight Transport Mode Choice using A Binary Logit Model

This study provides the first description of freight mode choice using the SARBAGITA area in Bali as a case study. A binary logit model was built to analyze the important factors influencing the choice between pick-up/box cars and medium/large trucks. This study found that the odds that drivers aged between 31 and 40 years old, elementary school as driver educational qualification, transported mining results, transported forest products and travel distance will use pick-up/box cars were 3.82, 6.54, 8.78, 18.08, and 1.05 times more likely than these of medium and large trucks. Meanwhile, the odds that freight transport vehicles owned by private, driver income was equal to regional minimum wage, and an average weight of transported goods were less than 5 tons will use pick-up/box cars were 34%, 28%, and 1% less likely than these of medium and large trucks.

Understanding market competition between transportation network companies using big data

As in a typical two-sided market, the competition between transportation network companies (TNCs) can lead to market fragmentation and loss of matching efficiency between passengers and drivers, whereas a monopoly market may result in the dominant TNC abusing its market power. Therefore, whether to encourage or discourage competition between TNCs is a debatable question for cities. Prior studies explored this question mostly through mathematical equilibrium models, but few have comprehensively investigated it based on empirical analysis using real-world data. To fill this gap, this study proposes a framework to measure and analyze the competition between TNCs using the most accessible ride-hailing trip data. Specifically, using an interpretable machine learning model, we investigate how TNCs’ pricing and wage strategies influence their market shares and how competition intensity affects passenger cost and driver income. The results based on large-scale trip records from four TNCs in New York City show that the pricing strategy is more influential than the wage strategy on the market shares and competition intensity. Instead of the top TNC, it is the strategies of challenger TNCs (with sizeable but not the biggest market shares) that affect the competition more. Both the passenger cost and driver income can benefit from competition even after considering the potential loss of matching efficiency, while TNCs’ profits shrink with growing competition intensity. These findings suggest that cities should encourage competition between TNCs, yet within a limit. They add empirical evidence to prior studies and provide implications for regulating TNC competition.

Predict GO-JEK Driver Income Level in the Bali Region using Decision Tree

The work in the transportation industry is one of several that is impacted by information technology, which is now developing quickly. The emergence of information technology in the transportation industry led to the creation of GO-JEK. GO-JEK is growing in popularity with the general public because, in addition to offering a wide range of services, it also creates new jobs with more flexible working hours for the community. Of course, each driver's income from working as a GO-JEK driver is unique. However, a number of things can have an impact on this income. With a focus on the Bali region, this study tries to forecast income levels for drivers of GO-JEK. J48 algorithm is used to process the data, producing a decision tree with 19 rule models. An accuracy value of 77.61%, a precision value of 78.95%, a value recall of 81.08%, and an AUC value of 0.808 are obtained from the rule model test utilizing the confusion matrix and ROC/AUC curve. These results demonstrate how effective the decision tree and rule model are.

Pengaruh Ojek Online: Faktor Faktor Yang Mempengaruhi Pendapatan Driver Gojek Dan Grab Di Kota Yogyakarta Tahun 2023 Dengan Metode Kualitatif

The effect of working hours, passenger targets, driver age, and fuel consumption on the income of Gojek and Grab drivers in Yogyakarta City. This study aims to determine the effect of the above variables on the income of Gojek and Grab drivers. The purpose of this research is expected to be useful and add insight for readers, besides that it can be a source of information about the factors that influence the income of Gojek and Grab drivers. In the research we conducted, the method we used was quantitative method. The data source used in this study is primary data obtained from the results of questionnaires distributed to Gojek and Grab drivers in Yogyakarta City. In this type of research using qualitative research using the classical assumption test in data processing. Driver working hours have a significant effect on income because the relationship between working hours and driver income has a significant positive relationship. Passenger targets do not have a significant influence on driver income. Driver age has a significant influence on driver income. Gasoline needs do not have a significant influence on the income of online motorcycle taxi drivers in Yogyakarta City. From the results of the analysis with the classical assumption test above, it can be concluded that working hours and driver age have a significant influence on the income of online ojek drivers. This is evidenced by the results of the classical assumption test conducted and produces a value that is in accordance with the requirements.

Analysis of Factors Affecting Go-Jek Driver Income during the Covid-19 Pandemic in Denpasar City

Transportation is an important element and serves as the lifeblood of life and economic, social, and political development, and population mobility. With all the problems regarding transportation and the needs of the community, the online motorcycle taxi was born, one of the companies that provide this service is PT. GO-JEK. However, at the end of 2019, the Coronavirus, or SARS-CoV2, commonly known as Covid-19 spread worldwide. In the Instruction of the Minister of Home Affairs No. 15 of 2021 concerning controlling the spread of Covid-19, the government adopted a policy to implement The Community Activities Restrictions Enforcement (CARE) aimed at recovering the economy of people affected by the Covid-19 pandemic. This research is quantitative in the form of associative. This research is located in Denpasar City. The population in this study are go-jek drivers in Denpasar City With 96 respondents. The analysis technique used in this research is descriptive statistical analysis. The study results show that incentives, working hours, work experience, and Emergency Community Activity Restrictions simultaneously affect the income of go-jek drivers in Denpasar City. Incentive variables, working hours, and work experience partially have a positive and significant effect on the income of go-jek drivers in Denpasar City. The Community Activities Restrictions Enforcement (CARE) partially have a negative effect on the income of go-jek drivers in Denpasar City

Disekuilibrium Kebijakan Transportasi Konvensional Dengan Transportasi Online Di Tangerang Selatan

Public policy is an alternative carried out by the government in dealing with problems that occur in society. The provision of public transportation services by the government with online transportation service providers still causes disquilibrium in the process of implementing public policy. PM 15 of 2019 with PM 118 of 2018 as a policy that regulates public transportation occurs disquilibrium in the policy, the existence of online transportation providing public transportation services finds losses on driver income and Regional Native Income as a public transportation levy, KIR test as a treatment of public transportation and a form of government supervision does not occur in online transportation, Vehicle storage facilities do not have to be owned by online transportation compared to must-have public/conventional transportation and vehicle maintenance and repair. From the various approaches that are widely proposed by many experts, this research will combine the tools of successful public policy implementation, namely 1) Communication 2) Goals 3) Program Implementation, 4) Implementation Context, 5) Compliance and Response. Qualitative research method with a descriptive approach with data collection techniques carried out through field observation, interviews and documentation. The result is that the transportation policy has a disquilibirum on one transportation service where the transportation manager has a difference of view between public services and profits, therefore disquilibriumbecomes evident in the implementation of the policy. In conclusion, the general transportation policy has its own goals in regulating driver operations, not in the transportation service manager

Pengaruh Layanan Go-Food, layanan Go-Send dan Bonus Insentif terhadap Pendapatan Driver Go-Jek Di Kota Padang Pasca Pandemi

This study aims to determine whether Go-Food services, Go-Send services, and incentive bonuses have an effect on Go-Jek driver income after the Pandemic. This data of research is quantitative research. The data collection method in this study used a questionnaire. The population of this study are all Go-Jek drivers in the city of Padang. The sample used in this study were Go-Jek drivers in the city of Padang who had met the criteria of reaching 97 people. The data analysis of this study used multiple linear regression analysis using the SPSS version 25 program. The results of this study indicate that Go-Food services, Go-Send services, and incentive bonuses have a positive and significant effect on the income of Go-Jek drivers in Padang City. Keywords: Go-Food Service, Go-send Service, Incentive Bonus and driver income

Dynamic Order Dispatching With Multiobjective Reward Learning

Traffic supply-demand mismatching has a severe impact on intelligent transportation systems. Fortunately, order dispatching is a promising option to mitigate the traffic supply-demand imbalance. Along this line, this article proposes the Multi-Driver Multi-Order Dispatching (MDMOD) method to make efficient order dispatching policy and enhance the experience of drivers and passengers. In the proposed MDMOD method, the Dynamic Multi-Objective Reward Learning (DMRL) algorithm is proposed to measure the driver-order-pair value, which illustrates the importance of a driver serving a specific order. A centralized matching algorithm is introduced to match all drivers and orders to maximize all driver-order-pair values. The multi-objective reward in the DMRL algorithm considers both immediate gains (i.e., pick-up distance) and future gains (i.e., the future traffic demand of order destination) to effectively improve the experience of drivers and passengers. Furthermore, by introducing the driver service level into the multi-objective reward, the “outstanding driver better reward” mechanism is realized to promote the ecological development of ride-sharing platforms. Notably, the Temporal-Graph Convolutional Network algorithm is proposed to predict the future traffic demand. Some virtual orders, which generated with the predicted future traffic demand, are dispatched to idle drivers to multiplex the traffic supply fully. A simulator is designed to test the performance of the proposed MDMOD method, experimental results demonstrate that the MDMOD method outperforms the state-of-the-art methods in terms of Average Driver Income and Order Response Rate.

Multi-agent reinforcement learning to unify order-matching and vehicle-repositioning in ride-hailing services

The popularity of ride-hailing platforms has significantly improved travel efficiency by providing convenient and personalized transportation services. Designing an effective ride-hailing service generally needs to address two tasks: order matching that assigns orders to available vehicles and proactive vehicle repositioning that deploys idle vehicles to potentially high-demand regions. Recent studies have intensively utilized deep reinforcement learning to solve the two tasks by learning an optimal dispatching strategy. However, most of them generate actions for the two tasks independently, neglecting the interactions between the two tasks and the communications among multiple drivers. To this end, this paper provides an approach based on multi-agent deep reinforcement learning where the two tasks are modeled as a unified Markov decision process, and the colossal state space and competition among drivers are addressed. Additionally, a modifiable agent-specific state representation is proposed to facilitate knowledge transferring and improve computing efficiency. We evaluate our approach on a public taxi order dataset collected in Chengdu, China, where a variable number of simulated vehicles are tested. Experimental results show that our approach outperforms seven existing baselines, reducing passenger rejection rate, driver idle time and improving total driver income.

Analisis distribusi pendapatan transporter online di Kota Jambi (studi kasus pengemudi gojek)

The first purpose determines the social and economic characteristics of Gojek drivers in Jambi City and the income distribution of Gojek drivers in Jambi City. The data analysis method used in this research is the quantitative method. Types of data, namely primary data and secondary data. Data collection techniques through interviews and questionnaires. The data that has been collected is processed by quantitative analysis and Gini Ratio, which is then presented in the form of descriptive analysis. Based on the results of the research, the social and economic characteristics of Gojek drivers in the city of Jambi include gender, age, education, marital status, number of dependents, working hours, work experience, work status, number of passengers, and income of Gojek drivers for one month. Gojek Driver's income distribution in Jambi City is low inequality. The results of the Gini analysis of the Gojek Driver's income ratio show the number 0.14. Meanwhile, the Lorenz curve shows that it is located not far from the diagonal or equalization line.

DAMPAK KENAIKAN TARIF OJEK ONLINE TERHADAP PENDAPATAN PENGEMUDI DAN KEPUASAN PENUMPANG, TINJAUAN SEBELUM PANDEMI COVID 19

Tariff and service are two important elements in online transportation. With the increase in rates, it will affect the income of drivers and passenger services. The purpose of this study is to determine the impact of the increase in online motorcycle taxi rates in 2019 when compared to 2018. Research in 2019 is a continuation of research in 2018. Data was obtained by conducting interviews with 200 passengers and 100 online motorcycle taxi drivers (Gojek) for each year. The impact of the tariff increase on driver's income is carried out by comparing the amount of income between 2019 and 2018. The Customer Satisfaction Index method was chosen to determine the service performance of online motorcycle taxis. Based on the analysis, the results show that the driver's income in the 2019 study has increased compared to 2018. In terms of service, the CSI value has increased. This shows that after the tariff increase, online motorcycle taxi transportation services are getting better

The Social, Economic, and Environmental Impacts of Ridesourcing Services: A Literature Review

The proliferation of ridesourcing services has raised both hopes and concerns about their role in cities. The impacts of ridesourcing services are complex and multi-faceted. Through reviewing the literature, this study aims to identify the social, economic, and environmental impacts of these services and highlight opportunities and challenges that lay ahead of them for resolving issues related to urban transportation. According to the results, ridesourcing services offer safe modes of transport that provide convenient mobility options, improve transit availability in disadvantaged and remote areas, and respond to taxi demand fluctuations. They can create new job opportunities by employing new human resources that have not been used before, provide flexible working hours for drivers, and are more efficient than taxi cabs. These services provide other opportunities to extend or complement public transit, reduce car ownership and congestion, and minimize parking supply. However, they are criticized for unfair competition with traditional taxis, limited compliance with social legislation, and lack of affordability. They are not available in all places and exclude some vulnerable and socially disadvantaged groups. Labor rights are not secure in this industry, and driver income is not stable. Finally, there is also evidence showing that, in some cases, they contribute to the growth of VMT, energy use, greenhouse gas emissions, and congestion in cities.

Analisis Faktor-Faktor yang Mempengaruhi Pendapatan Driver Go-Ride pada Masa Pandemi Covid-19 di Gorontalo

Online transportation is a means of transportation based on a particular application, where consumers order transportation through the application system on a smartphone which makes it very easy for users. This study aims to examine and analyze the effect of incentives on Go-Ride drivers, the effect of input from service transactions on Go-Ride drivers and to see the effect of flextime on drivers on Go-Ride in Gorontalo. The research method used is quantitative research methods. The research subjects in this study were Go-Ride drivers who were active in Gorontalo. The sample in this study was determined based on incidental sampling. The data analysis technique used by researchers is multiple regression analysis with partial hypothesis testing, namely the t test and the coefficient of determination (Adjusted R Square). The results showed that incentives have a positive effect on driver's income on Go-Ride in Gorontalo, the number of service transactions that affect driver's income on Go-Ride in Gorontalo and Flextime have a positive effect on drivers on Go-Ride in Gorontalo. The acquisition of a determinant value (Adjusted R Square) of 65.3% for Go-Ride drivers in Gorontalo. While the rest amounted to 34.7%. By other variables not included in this study

Analisis Faktor-Faktor yang Mempengaruhi Pendapatan Driver Grab-Bike

The purpose of this study is, (1) To find out how the characteristics of Grabbike drivers in Banjarmasin City. (2) To find out whether the type of service, frequency of delivery, and age influence the income of Grabbike drivers in Banjarmasin City. (3) To find out which factor is the most dominant influence on the income of Grabbike drivers in Banjarmasin City.This type of research uses quantitative descriptive methods by collecting data using Primary Data. Independent variables or independent variables in this study include service type (x1), delivery frequency (x2), and age (x3), and the dependent variable or dependent variable in this study is Grab-bike Driver Income. This research was conducted in Banjarmasin City precisely in January 2020. The data collection method used purposive sampling combined with accidental sampling through questionnaires, interviews, literature studies, and documentation. Data Analysis Techniques use the form of econometrics by regressing existing variables using Multiple Linear Regression analysis, which will involve more than one predictor or independent variable and will also use the OLS method to test all independent variables on the dependent variable.The conclusions of this study are 1.a) Based on the age characteristics of the respondents, it shows that respondents aged between 21-30 years were the most dominant, as many as 16 respondents with a percentage of 53.33%. b) Based on the gender characteristics of the respondents, it shows that all respondents totaling 30 people are male with a percentage of 100%. c) Based on the respondents' education level characteristics, it shows that respondents who graduated from high school were the most dominant, as many as 24 people with a percentage of 80% 20 people with a percentage of 66.67%. e) Based on the table of income characteristics of respondents, it shows that respondents who earn more than 3 million are the most dominant, as many as 21 people with a percentage of 70%. 2. The delivery frequency variable has a positive and significant effect on the income of grab bike drivers in Banjarmasin. In contrast, the service type and age variables do not have a positive and not significant effect on the income of grab bike drivers in Banjarmasin. 3. The delivery frequency variable has the most dominant influence on the income of grab bike drivers in Banjarmasin City.