Worrawat Saijai

Dr. Worrawat Saijai


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
17 April 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
KPKansuda Pankwaen
Kansuda Pankwaen
STSukrit Thongkairat
Sukrit Thongkairat
WSWorrawat Saijai
Worrawat Saijai
This study presents an advanced adaptive trading framework that integrates Deep Reinforcement Learning (DRL) with the Iterative Model Combining Algorithm (IMCA) to overcome the critical limitations of static ensemble methods in global portfolio optimization. Using a diverse cross-market dataset of 39 stocks from the US, Australia, Europe, Thailand, and one cryptocurrency (BTC-USD), the research rigorously evaluates models’ adaptability under volatile market conditions. Volatile market conditions—such as COVID-19, SVB crisis, and the 2022 crypto crash—are captured via volatility metrics (e.g., drawdown), with DRL models like PPO/TD3 adapting through dynamic reward signals. This cross-asset integration is particularly critical, as it captures the complex dynamics and correlations between traditional financial markets and emerging digital assets. Although DRL models like PPO and TD3 outperform traditional strategies, they remain vulnerable to market drawdowns and high volatility. IMCA significantly surpasses these models, achieving the highest cumulative return of 29.52% and a superior Sharpe ratio of 0.829 by dynamically recalibrating model weights in response to real-time market dynamics. This study addresses a substantial research gap, highlighting the failure of traditional ensemble models—reliant on static weightings—to adapt to evolving financial conditions, resulting in suboptimal risk-adjusted returns. IMCA offers a dynamic, data-driven approach that continuously optimizes portfolio strategies across fluctuating market regimes, demonstrating its scalability and robustness across diverse asset classes and regional markets, and providing an empirical framework for adaptive portfolio management. Policy recommendations underscore the need for financial institutions to adopt AI-driven adaptive models like IMCA to enhance portfolio resilience, profitability, and responsiveness in uncertain markets.

17 March 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
KPKansuda Pankwaen
Kansuda Pankwaen
STSukrit Thongkairat
Sukrit Thongkairat
WSWorrawat Saijai
Worrawat Saijai
This study presents an advanced adaptive trading framework that integrates Deep Reinforcement Learning (DRL) with the Iterative Model Combining Algorithm (IMCA) to overcome the critical limitations of static ensemble methods in global portfolio optimization. Using a diverse cross-market dataset of 39 stocks from the US, Australia, Europe, Thailand, and one cryptocurrency (BTC-USD), the research rigorously evaluates models’ adaptability under volatile market conditions. This cross-asset integration is particularly critical, as it captures the complex dynamics and correlations between traditional financial markets and emerging digital assets. Although DRL models like PPO and TD3 outperform traditional strategies, they remain vulnerable to market drawdowns and high volatility. IMCA significantly surpasses these models, achieving the highest cumulative return of 29.52% and a superior Sharpe ratio of 0.8293 by dynamically recalibrating model weights in response to real-time market dynamics. This study addresses a substantial research gap, highlighting the failure of traditional ensemble models—reliant on static weightings—to adapt to evolving financial conditions, resulting in suboptimal risk-adjusted returns. IMCA offers a dynamic, data-driven approach that continuously optimizes portfolio strategies across fluctuating market regimes, demonstrating its scalability and robustness across diverse asset classes and regional markets, and providing an empirical framework for adaptive portfolio management. Policy recommendations underscore the need for financial institutions to adopt AI-driven adaptive models like IMCA to enhance portfolio resilience, profitability, and responsiveness in uncertain markets.

19 May 2026 in Economies
Verified
Journal Article
Open access
PDF file
NWNgu Wah Win
Ngu Wah Win
SLSupanika Leurcharusmee
Supanika Leurcharusmee
WSWorrawat Saijai
Worrawat Saijai
This paper examines how remittances-to-GDP are conditionally associated with GDP growth upswings and downturns in four lower-middle-income countries (LMICs) in mainland Southeast Asia—Cambodia, Laos, Myanmar, and Vietnam (CLMV)—over 2000–2021, conditional on other external inflows including foreign direct investment (FDI), official development assistance (ODA), and trade openness. Employing a nonlinear Autoregressive Distributed Lag (N-ARDL) model with a Dynamic Fixed Effects (DFE) estimator, this study estimates short- and long-run regime-differentiated associations between GDP growth regimes and remittances to GDP, controlling for foreign direct investment (FDI), official development assistance (ODA), and trade openness. GDP growth is decomposed into above- and below-median regimes, allowing the model to examine whether remittance dynamics differ across growth upswings and downturns. Panel estimates are complemented with dynamic multipliers that trace conditional adjustment paths over different horizons. The results reveal a high-growth-driven regime pattern rather than formal statistical evidence of unequal high- and low-growth coefficients. In the long run, above-median growth significantly reduces remittances to GDP (θ^1=−0.130, very strong evidence), consistent with the household insurance motive; below-median growth has no significant long-run association (θ^2=−0.127, no evidence). In the short run, above-median growth is positively associated with remittances (β˜^1+=0.033, very strong evidence), while below-median growth again shows no significant short-run response (β˜^1−=0.051, no evidence). Formal Wald tests do not reject equality between the high- and low-growth coefficients in either horizon; therefore, the findings should be interpreted as a regime-differentiated significance pattern within a nonlinear specification, not as formal proof of coefficient asymmetry. Taken together, these responses are consistent with a one-sided counter-cyclical interpretation of remittances: remittances to GDP decline when domestic growth is above the median, while no significant adjustment is observed during below-median growth episodes. The pattern documented here is therefore driven by the high-growth regime and should not be read as evidence of an active counter-cyclical surge during downturns. Trade openness and ODA exhibit significant positive short-run co-movement with remittances, whereas FDI shows a strong positive long-run association with remittances to GDP. The novelty of this study lies in providing new panel evidence on regime-differentiated remittance–growth associations for CLMV within a nonlinear N-ARDL and dynamic multiplier framework, while transparently reporting that formal Wald tests do not reject equality between high- and low-growth coefficients. Policy implications center on facilitating reliable remittance channels—reducing transfer costs and expanding financial inclusion—without assuming that remittance inflows automatically rise during downturns.


6 August 2026 in Economies
Verified
Journal Article
Open access
PDF file
NTNaw Htee Thaw Thaw
Naw Htee Thaw Thaw
KPKansuda Pankwaen
Kansuda Pankwaen
NWNgu Wah Win
Ngu Wah Win
WSWorrawat Saijai
Worrawat Saijai
After the 2021 military coup in Myanmar, many people sought safety, decent work, and social protection in neighboring Thailand. This study examines how legal documentation status and Sense of Place (SOP) are associated with the workplace retention intentions of irregular Myanmar migrant workers in Mae Sot, Thailand. SOP is conceptualized through three key dimensions: emotional bonds to the surrounding environment (place attachment), the extent to which the place meets everyday needs (place dependence), and the way migrants identify with their host context (place identity). To explore these dynamics, we adopted an explanatory sequential mixed-methods approach, surveying 101 respondents between January and April 2024 and subsequently conducting in-depth interviews with 30 individuals between June and July 2024. Given the sensitivity of irregular migration and undocumented legal status, obtaining survey responses was challenging because many potential participants were concerned about privacy, identification, and possible legal exposure. Quantitative data were analyzed using descriptive comparisons, bivariate association tests with Goodman-calibrated minimum Bayes factors, LASSO-assisted variable screening, principal component analysis, and Bayesian mixed-effects ordinal probit models. The descriptive and bivariate results show that legal documentation status is positively associated with all SOP dimensions, job satisfaction, and willingness to remain in the current job. In the candidate model comparison, the Bayesian specification without legal status showed slightly better predictive performance than the corresponding specification with legal status. The primary five-category Bayesian mixed-effects model indicated positive conditional associations of Job Satisfaction, Place Attachment, and the structural workplace index with willingness to stay. It also indicated heterogeneity in the Place Attachment association across observed job tenure groups; this pattern is interpreted as a cross-sectional between-group difference rather than as evidence of individual change over time. Complementary Bayesian sensitivity analyses evaluate the multidimensional SOP construct, the incremental predictive contribution of legal status, sensitivity to alternative priors, and model diagnostics. The qualitative interviews further show that legal documentation is widely perceived as enabling broader employment opportunities, safer access to basic services, employer support, labor rights protection, and reduced exposure to exploitation. Overall, this study highlights the complementary roles of legal recognition, workplace satisfaction, and emotional rootedness in shaping migrant retention, offering implications for decent work, migrant well-being, reduced inequalities, and sustainable labor and migration policies in Thailand’s border regions, particularly in relation to SDG 8 and SDG 10.