Applications of Machine Learning in Revenue Management and Routing
Bibliographic record
Abstract
In this thesis, I use machine learning techniques to solve issues in revenue management and public transportation design. The first two chapters relate to problems of revenue management and online learning. The problem of sequential learning and optimization of the demand function has been an important topic in revenue management. Finding the optimal policy faces numerical complexity and is prone to the curse of dimensionality. It is mostly solved using heuristics and restrictive assumptions. In the first chapter, I use a novel non-parametric approach to solving dynamic pricing and learning problems. I develop a flexible method to approximate the optimal policy using polynomial approximation, thus reducing complexity. I make use of the Bayesian framework to update the probability model and make advances in numerical methods to solve this problem. In the second chapter, I use a machine learning heuristic called Thompson sampling. I improve the performance of the heuristic over short horizons by enforcing the decreasing nature of the demand function in the sampling algorithm. Using a stylized proof, I demonstrate the performance gains associated with this method and show the merits of ordered sampling with Thompson Sampling over short horizons. The last chapter makes use of a machine learning approach called data envelopment analysis (DEA), which I use in designing new public transportation routes in rural regions. I develop algorithms and heuristics to balance cost and equity under multiple objectives. The solution to this project was implemented in the city of Quinte West, Ontario.
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 | 0.003 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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".