Varun Sarda

Dr. Varun Sarda

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
17 October 2025 in AI
Verified
Journal Article
Open access
PDF file
SRShlok Sagar Rajpal
Shlok Sagar Rajpal
RMRajesh Mahadeva
Rajesh Mahadeva
Amit Kumar GoyalAmit Kumar Goyal
Amit Kumar Goyal
VSVarun Sarda
Varun Sarda
This study presents a novel approach to financial time series forecasting by introducing asymmetric loss functions. This is specifically designed to enhance directional accuracy across major stock indices (S&P 500, DJI, and NASDAQ Composite) over a 33-year time period. We integrate these loss functions into an attention-based Long Short-Term Memory (LSTM) framework. The proposed loss functions are evaluated against traditional metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), and other recent research-based losses. Our approach consistently achieves superior test-time directional accuracy, with gains of 3.4–6.1 percentage points over MSE/MAE and 2.0–4.5 percentage points over prior asymmetric losses, which are either non-differentiable or require extensive hyperparameter tuning. Furthermore, proposed models also achieve an F1 score of up to 0.74, compared to 0.63–0.68 for existing methods, and maintain competitive MAE values within 0.01–0.03 of the baseline. The optimized asymmetric loss functions improve specificity to above 0.62 and ensure a better balance between precision and recall. These results underscore the potential of directionally aware loss design to enhance AI-driven financial forecasting systems.

20 March 2025 in Agricultural and Resource Economics: International Scientific E-Journal
Verified
Journal Article
Open access
PDF file
Ganeshkumar D. RedeGaneshkumar D. Rede
Ganeshkumar D. Rede
PSPallawi Sangode
Pallawi Sangode
RDRamkrishna Dikkatwar
Ramkrishna Dikkatwar
VSVarun Sarda
Varun Sarda
HSHari Babu Singu
Hari Babu Singu
Purpose. Given the urgent need to save the planet, countries are striving to achieve the UN Sustainable Development Goals (SDGs). Agriculture is one of the sectors that contributes to the achievement of these goals on a global scale. As practices in this sector change, direct impacts on soil, air and water are evident, calling into question the sustainability of these practices. Furthermore, food security or food availability is also directly linked to the achievement of the SDGs. With limited research, this study examines the relationship between food security, agriculture, and SDGs. Methodology / approach. This research conducted a bibliometrics analysis from two databases, Web of Science (WoS), with 1450 papers and Scopus 463 documents for 10 years from 2014 to May 2024. Key parameters are identified and ranked, including highly productive authors, countries, disciplines, and institutions. The bibliometric software VOSviewer was used to perform co-word analysis and identify research clusters. Results. The research findings indicate that the United States, followed by India and China, have demonstrated the highest levels of publication activity within the field. The literature predominantly emphasises the SDGs, particularly Zero Hunger, Climate Action, and Life on Land, through the lens of agriculture and food security. The study underscores the leadership of the United States, India, and China in agricultural research, highlighting the critical necessity for concerted collaboration among researchers, policymakers, and practitioners to foster a transformative food system globally. The findings suggest that agriculture is crucial in attaining food security by guaranteeing sustainable food production, combating hunger, and encouraging activities that improve environmental conservation – all critical for long-term food availability –because of SDG 2: Zero Hunger. Originality / scientific novelty. This paper stands out for its originality as, by using bibliometric analysis, the study systematically maps the scientific literature and uncovers nuanced connections between food security, agriculture, and SDGs. Such an analysis has not yet been widely documented. This study contributed to a deeper understanding of the relationships and dynamics shaping global efforts to achieve food security and sustainable agriculture. Practical value / implications. This study offers a new perspective on how these critical areas of food security, agriculture, and SDGs interplay and evolve, providing crucial insights for policymakers, researchers, and practitioners alike. Moreover, the paper contributes to the academic discourse by synthesising trends, identifying gaps, and suggesting future research directions, paving the way for informed decision-making and impactful interventions in global food security and sustainable agriculture efforts.

28 October 2025 in Journal of Transport and Supply Chain Management
Verified
Journal Article
Open access
PDF file
NMNarayana Maharana
Narayana Maharana
SCSuman Kalyan Chaudhury
Suman Kalyan Chaudhury
Ashok Kumar PanigrahiAshok Kumar Panigrahi
Ashok Kumar Panigrahi
MUMinal Uprety
Minal Uprety
BPBiswaranjan Parida
Biswaranjan Parida
SDSmruti R. Das
Smruti R. Das
Background: The Indian millet sector remains fragmented and inefficient, constraining effective supply chain performance. With growing recognition of millets’ role in food security and rural livelihoods, enhancing operational efficiency through lean practices has become crucial. Objectives: This study identifies and analyses the combinations of conditions that lead to high and low lean supply chain performance (LSCP) in millet distribution across India, addressing key operational challenges in agri-food supply chains. Method: Using fuzzy-set qualitative comparative analysis (fsQCA), the study evaluates six core conditions: technology integration, farmer coordination, market linkage (ML), inventory control, waste reduction (WR), and standardised processes. Primary data were collected from 132 respondents through structured surveys and field-level expert inputs, and configurations leading to both high and low LSCP were examined based on raw and unique coverage and consistency values. Results: The analysis reveals multiple sufficient pathways for achieving high LSCP, particularly configurations that combine ML, inventory control, and WR. Technology integration is a sufficient but not a necessary condition, suggesting its effectiveness is context specific. Conversely, the absence of ML, WR, and inventory control consistently contributes to low LSCP. Conclusion: The fsQCA provides a systematic approach to understanding the configurational dynamics influencing supply chain performance in millet distribution. Operational practices such as ML, inventory control, and WR exert greater influence than standardisation or technology in isolation. Contribution: The findings offer practical insights for policymakers and supply chain actors, highlighting the need for integrated strategies that strengthen market access, storage infrastructure, and post-harvest efficiency.

Verified
Journal Article
Open access
PDF file
ASAvi Singh
Avi Singh
RMRajesh Mahadeva
Rajesh Mahadeva
VSVarun Sarda
Varun Sarda
Amit Kumar GoyalAmit Kumar Goyal
Amit Kumar Goyal
The global economy frequently experiences cycles of rapid growth followed by abrupt crashes, challenging economists and analysts in forecasting and risk management. Crashes like the dot-com bubble crash and the 2008 global financial crisis caused huge disruptions to the world economy. These crashes have been found to display somewhat similar characteristics, like rapid price inflation and speculation, followed by collapse. In search of these underlying patterns, the Log-Periodic Power-Law (LPPL) model has emerged as a promising framework, capable of capturing self-reinforcing dynamics and log-periodic oscillations. However, while log-periodic structures have been tested in developed and stable markets, they lack validation in volatile and developing markets. This study investigates the applicability of the LPPL framework for modeling financial crashes in the Brazilian stock market, which serves as a representative case of a volatile market, particularly through the Bovespa Index (IBOVESPA). In this study, daily data spanning 1993 to 2025 is analyzed to model pre-crash oscillations and speculative bubbles for five major market crashes. In addition to the traditional LPPL model, autoregressive residual analysis is incorporated to account for market noise and improve predictive accuracy. The results demonstrate that the enhanced LPPL model effectively captures pre-crash oscillations and critical transitions, with low error metrics. Eigenstructure analysis of the Hessian matrices highlights stiff and sloppy parameters, emphasizing the pivotal role of critical time and frequency parameters. Overall, these findings validate LPPL-based nonlinear modeling as an effective approach for anticipating speculative bubbles and crash dynamics in complex financial systems.

27 January 2026 in Acta Psychologica
Verified
Journal Article
Open access
DSDeepmala Singh
Deepmala Singh
SGShwetam Gupta
Shwetam Gupta
VSVarun Sarda
Varun Sarda
Dark personality leaders are known for their detrimental effects in the workplace. Through comprehensive meta-analysis this paper analyzes the impact of abusive leadership on employee and organisational outcomes using 39 independent studies with a total of 32,909 participants. Using a Hunter-Schmidt methodology, we examined the associations between abusive leadership behaviours and outcome variables capturing employee well-being, organisational commitment, and job performance through a random-effects meta-analysis. The results indicate the expected abusive leadership is a negative predictor of employee-related outcomes, as well as job performance indicators and commitment towards the organisation. These findings have important implications for organisational policy, leadership training programs, and intervention tools to reduce the effects of abusive leadership in the workplace.

24 April 2026 in Array
Verified
Journal Article
Open access
ITItikirala Prem Tejas
Itikirala Prem Tejas
AGAmit Kumar Goyal
Amit Kumar Goyal
RMRajesh Mahadeva
Rajesh Mahadeva
VSVarun Sarda
Varun Sarda