R. Sofia
R. Sofia has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Anand Chauhan
Rutgers Business School, Rutgers University,Newark,NJ,USA,07102
1 shared publication - G. Subashini
Department of Business Management Sri Padmavati Mahila Visvavidyalayam Andhra Pradesh 517502 Tirupati India
1 shared publication Hatim Kagalwala
1 shared publicationHeena Kousar
East Point College of Engineering and Technology,Department of Computer, Science and Engineering,Bengaluru
1 shared publication- Rajesh Sadhwani
Department of Management Studies. Indukaka Ipcowala Institute of Management CHARUSAT University Off. Nadiad-Petlad Highway 388421 Changa Anand Gujarat India
1 shared publication - Rohit Bansal
Associate Professor, Mittal School of Business, Lovely Professional University, Phagwara, India
1 shared publication
Latest Publications
- 9 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Reinforcement Learning-Optimized Dynamic Pricing Models for EV Charging Stations in Real Time
Dynamic pricing is essential for managing demand, maximizing revenue and consumer satisfaction when it pertains to electric vehicle (EV) charging stations. Dynamic pricing is just one of possibly many methods to learn from the context and consumer behavior in real-time and dynamically adapt pricing strategies with an approach based on Reinforcement Learning (RL). While the authors show that there has been a limited amount of RL-based EV charging station dynamic pricing work that shows sound forecasting and stochastic optimization approaches, most of the current methods rely on either static models or rules to set prices. Rules are often weak models that are not very good at accounting for consumer heterogeneity real-time adjustments due at minimum to demand variability, and capacity constraints of the grid. Through inflexible models and limitations, owners could lose out on revenue per charge, charge intervals, and charging locations. The Reinforcement Learning-Optimized Dynamic Pricing Framework (RLO-DPF) involves dynamic pricing. The dynamic pricing system is adaptive because it uses reinforcement learning to tune its parameters depending on the characteristics of grid stability, charge demand, and available energy for adopters in the case of dynamic pricing and policy adaptation. Prices at the EV charging station will dynamically adapt to current market conditions through dynamic pricing optimization, operational efficiency and deep RL. The RLO-DPF provides a dynamic pricing point that considers the best of both worlds by balancing stress of peak load and charging station utilization. The RLODPF will be advantageous for charging operators to provide reduced charges and still be profiting. Further, by connecting to renewable power output, electric vehicle (EV) infrastructure will become easier. Rather than using previous methods, the RLO-DPF improved real-world simulations for resource distribution, customer wait times, and profit margins.
- 9 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Reinforcement Learning-Optimized Dynamic Pricing Models for EV Charging Stations in Real Time
Dynamic pricing is essential for managing demand, maximizing revenue and consumer satisfaction when it pertains to electric vehicle (EV) charging stations. Dynamic pricing is just one of possibly many methods to learn from the context and consumer behavior in real-time and dynamically adapt pricing strategies with an approach based on Reinforcement Learning (RL). While the authors show that there has been a limited amount of RL-based EV charging station dynamic pricing work that shows sound forecasting and stochastic optimization approaches, most of the current methods rely on either static models or rules to set prices. Rules are often weak models that are not very good at accounting for consumer heterogeneity real-time adjustments due at minimum to demand variability, and capacity constraints of the grid. Through inflexible models and limitations, owners could lose out on revenue per charge, charge intervals, and charging locations. The Reinforcement Learning-Optimized Dynamic Pricing Framework (RLO-DPF) involves dynamic pricing. The dynamic pricing system is adaptive because it uses reinforcement learning to tune its parameters depending on the characteristics of grid stability, charge demand, and available energy for adopters in the case of dynamic pricing and policy adaptation. Prices at the EV charging station will dynamically adapt to current market conditions through dynamic pricing optimization, operational efficiency and deep RL. The RLO-DPF provides a dynamic pricing point that considers the best of both worlds by balancing stress of peak load and charging station utilization. The RLODPF will be advantageous for charging operators to provide reduced charges and still be profiting. Further, by connecting to renewable power output, electric vehicle (EV) infrastructure will become easier. Rather than using previous methods, the RLO-DPF improved real-world simulations for resource distribution, customer wait times, and profit margins.
- Open Access
- 21 March 2023
- Published by Conselho Nacional de Pesquisa e Pos-Graduacao em Direito - CONPEDI in International Journal of Professional Business Review
- Vol. 8 (4) , e01241
A Study on the Association of Entrepreneurship Ecosystem with Financial Inclusion
Purpose: The purpose of this study is to examine the association of entrepreneurship ecosystem with financial inclusion, and to explore the potential ways in which the ecosystem can be leveraged to improve access to financial services for marginalized communities. Theoretical framework: The study utilizes the ecosystem approach to entrepreneurship, which emphasizes the interdependence and interplay of various stakeholders in the entrepreneurial process. The study also draws on the concept of financial inclusion, which refers to the provision of affordable and accessible financial services to all individuals and businesses. Design/methodology/approach: The study employs a mixed-methods approach, including a literature review, case studies, and surveys, to collect data from a variety of stakeholders in the entrepreneurship ecosystem. Findings: The findings suggest that the entrepreneurship ecosystem plays a critical role in promoting financial inclusion. The ecosystem can be leveraged to increase access to financial services for marginalized communities through the development of innovative financial products and services, the creation of mentorship and networking opportunities, and the promotion of policies that encourage financial inclusion. Research, practical and social implications: The study contributes to the understanding of the relationship between entrepreneurship and financial inclusion, and has implications for policymakers and practitioners seeking to promote financial inclusion through entrepreneurship. The findings can also inform the design and implementation of programs and policies aimed at promoting entrepreneurship and financial inclusion in marginalized communities. Originality/value: The study is among the first to examine the association of entrepreneurship ecosystem with financial inclusion and to explore the potential ways in which the ecosystem can be leveraged to improve access to financial services for marginalized communities.
- 21 March 2023
- Published by Conselho Nacional de Pesquisa e Pos-Graduacao em Direito - CONPEDI in International Journal of Professional Business Review
- Vol. 8 (4) , e01241
Open AccessA Study on the Association of Entrepreneurship Ecosystem with Financial Inclusion
Purpose: The purpose of this study is to examine the association of entrepreneurship ecosystem with financial inclusion, and to explore the potential ways in which the ecosystem can be leveraged to improve access to financial services for marginalized communities. Theoretical framework: The study utilizes the ecosystem approach to entrepreneurship, which emphasizes the interdependence and interplay of various stakeholders in the entrepreneurial process. The study also draws on the concept of financial inclusion, which refers to the provision of affordable and accessible financial services to all individuals and businesses. Design/methodology/approach: The study employs a mixed-methods approach, including a literature review, case studies, and surveys, to collect data from a variety of stakeholders in the entrepreneurship ecosystem. Findings: The findings suggest that the entrepreneurship ecosystem plays a critical role in promoting financial inclusion. The ecosystem can be leveraged to increase access to financial services for marginalized communities through the development of innovative financial products and services, the creation of mentorship and networking opportunities, and the promotion of policies that encourage financial inclusion. Research, practical and social implications: The study contributes to the understanding of the relationship between entrepreneurship and financial inclusion, and has implications for policymakers and practitioners seeking to promote financial inclusion through entrepreneurship. The findings can also inform the design and implementation of programs and policies aimed at promoting entrepreneurship and financial inclusion in marginalized communities. Originality/value: The study is among the first to examine the association of entrepreneurship ecosystem with financial inclusion and to explore the potential ways in which the ecosystem can be leveraged to improve access to financial services for marginalized communities.