ADVANCED OP T IMIZAT ION T ECHNIQUE S IN DYNAMIC PORT FOL IO S TRAT EGI E S , PAIR TRADING,AND CARBON DIOXIDE EMI S S ION MODE L ING
Bibliographic record
Abstract
This thesis explores advanced optimization modeling techniques withapplications in three key areas of sustainable finance: dynamic portfolio construction through market state classification, pair trading strategies in financial markets, and carbon dioxide emission modeling. We develop a clustering algorithm for Bayesian Markov Switching Models to classify markets into volatility-based states, optimizing asset allocation strategies by identifying distinct market regimes. Additionally, we performed mixing time and convergence analysis to assess the efficiency and stability of the model. This approach incorporates equal-weighted investment, minimum variance, maximum diversification, and equal risk contribution strategies, demonstrating superior risk-adjusted returns compared to static strategies. We also introduce a Multi-modal Temporal Relation Graph Learning (MTRGL) framework, which integrates time-series and categorical data through a dynamic graph and memory-enhanced dynamic graph neural network to identify time-dependent correlations among financial instruments. This method reframes pair trading as a temporal graph link prediction problem, outperforming traditional methods in empirical tests. Furthermore, we conducted a convergence analysis of the MTRGL framework, evaluating the model’s convergence rate and complexity to ensure efficient and stable solutions. Finally, we propose an optimization framework that combines Support Vector Machine (SVM) regression and Principal Component Regression (PCR) to analyze socioeconomic and environmental factors affecting carbon dioxide emissions, refining emission models and informing sustainability policies. Our findings highlight the effectiveness of these optimization techniques in forecasting carbon dioxide emissions, enhancing pair trading reliability, and optimizing investment strategies, thereby contributing to advancements in both environmental and quantitative finance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".