Prasanta Chatterjee Biswas

Prasanta Chatterjee Biswas

Auto-generated profile, based on publicly available information

Prasanta Chatterjee Biswas

Parul University, Vadodara, India

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 March 2026
Verified
Book Chapter
Open access
PDF file
UGUdayan Giri
Udayan Giri
ASAnil Sharma
Anil Sharma
RTRenny Thomas
Renny Thomas
GCGanesh Chavan
Ganesh Chavan
PBPrasanta Chatterjee Biswas
Prasanta Chatterjee Biswas
India's fast-moving consumer goods (FMCG) industry is undergoing significant transformation, primarily fueled by digitalization. This shift is supported by growing internet access, the widespread adoption of affordable mobile technologies, and evolving consumer expectations. With over 800 million internet users, digital platforms have become central to brand–consumer interactions, yet consumer behaviour in FMCGs remains complex, characterised by frequent, low-involvement purchases that are highly sensitive to promotions, peer influence, and convenience. While previous studies have examined digital adoption broadly, limited research has systematically assessed how specific digital marketing drivers—social media influencers, convenience, and price offers—shape consumer buying behaviour in the FMCG context. The study employed a quantitative research design and collected data from 203 participants through a structured questionnaire. All constructs were assessed using a Likert scale, and the proposed framework was tested using Partial Least Squares–Structural Equation Modelling (PLS-SEM). Reliability analysis confirmed high internal consistency Cronbach's α = 0.973, while confirmatory factor analysis validated the measurement model. The results revealed that price offers exert the strongest influence on consumer buying behaviour β = 0.54, p < 0.05, followed by convenience β = 0.20, p < 0.05, whereas social media influencers showed a comparatively weaker effect β = 0.19, p < 0.05. The study offers practical insights for FMCG marketers to design targeted digital strategies that balance affordability with convenience and trust. Policy recommendations include strengthening digital literacy, promoting responsible influencer advertising, and expanding digital infrastructure to support inclusive consumer engagement. The findings contribute to both managerial practice and academic understanding of digital consumer behaviour in emerging economies. <!----> <!----> <!----> <!---->

20 February 2026
Verified
Book Chapter
Closed access
KJK. A. Jayabalaji
K. A. Jayabalaji
SAS. Venkata Anand
S. Venkata Anand
DRDineshkumar Rajendran
Dineshkumar Rajendran
PBPrasanta Chatterjee Biswas
Prasanta Chatterjee Biswas
SOSardor Omonov
Sardor Omonov
RARubaid Ashfaq
Rubaid Ashfaq
Quantum machine learning (QML) has become an optimistic avenue of harnessing quantum computation in data-driven modeling, especially of issues with high dimensionality and complicated correlations. Current methods are generally based on fixed or over-parameterized quantum circuits, and hence restricted to scalability as well as unproductive optimization in real-world hardware. This chapter introduces a hybrid quantum-classical learning system that is adaptive and provides principled quantum data encoding, architecture-conscious variational circuit design and resource-optimal optimization. The technique is based on the concepts of quantum architecture search and subspace-preserving transformations to trade expressiveness with trainability, and discretize the quantum model into a classical pipeline processing system to make it robust and flexible. The experimental analysis proves that the suggested framework is more accurate in its classification and converges more quickly than the representative variational and convolutional quantum models.

3 November 2026
Verified
Book Chapter
Closed access
TST. Aditya Sai Srinivas
T. Aditya Sai Srinivas
MAM. Amshavalli
M. Amshavalli
PBPrasanta Chatterjee Biswas
Prasanta Chatterjee Biswas
PGPrasanthi Gottumukkala
Prasanthi Gottumukkala
AAA. Aiswarya
A. Aiswarya
VBV. Bhoopathy
V. Bhoopathy
This research addresses predictive analytics for proactive risk identification and management across sectors. Using time series analysis, ML algorithms, and Chi-square testing, the study found that financial forecasting models are accurate, with credit scoring models being 85% accurate. The study reveals that predictive analytics-based frameworks considerably improve an organization's resilience. To boost forecast accuracy, businesses should integrate real-time data, use adaptive algorithms, and customise models for their sector. ML-based predictive analytics can forecast, plan for, and reduce these issues. This chapter discusses ML in predictive analytics and how firms may leverage data-driven insights to become more resilient and ready for anything. ML approaches including supervised learning, unsupervised clustering, and DL architectures are examined for disruption prediction. Real-world examples demonstrate how things work, and discussions of challenges and trends encourage research and industry use.

23 May 2026
Verified
Conference Paper
Closed access
PBP. Balaji
P. Balaji
VMViyyapu Mounika
Viyyapu Mounika
DSDeepti Sharma
Deepti Sharma
PBPrasanta Chatterjee Biswas
Prasanta Chatterjee Biswas
APAneesya Panicker
Aneesya Panicker
ASAvnish Sharma
Avnish Sharma

13 March 2026
Verified
Book Chapter
Closed access
SSS. Surya
S. Surya
DRD. Mahammad Rafi
D. Mahammad Rafi
NCNeeraj Chandnani
Neeraj Chandnani
PBPrasanta Chatterjee Biswas
Prasanta Chatterjee Biswas
MTMohit Tiwari
Mohit Tiwari
MLMelanie Elizabeth Lourens
Melanie Elizabeth Lourens
Artificial intelligence has become sufficiently advanced that classical deep learning architectures can no longer easily support the needs in terms of scale, energy efficiency and interpretability. The traditional models are strong, but they are limited by physical and computational constraints of the classical hardware, which limits their capacity to learn efficiently using complex and high-dimensional data. This paper fills the said gap by proposing a Hybrid Quantum Neural Network (QNN) architecture that combines both quantum information processing with classical optimization. In contrast to previously hybrid or variation methods to quantum control, the model proposed incorporates adaptive entanglement control, quantum regularization, and circuit-depth compression, which allows obtaining stable learning in noisy intermediate-scale quantum (NISQ)-conditions. Empirical assessments showed that the accuracy had been improved by 3.7 percent, a 43 percent decrease in energy usage, and convergence was quickened as compared to known benchmarks,

23 May 2026
Verified
Conference Paper
Closed access
NPNaveen Pol
Naveen Pol
SCShiney Chib
Shiney Chib
GGG. Gowri
G. Gowri
PBPrasanta Chatterjee Biswas
Prasanta Chatterjee Biswas
TJT. Jayapratha
T. Jayapratha
BGB. T. Geetha
B. T. Geetha