A predictive and prescriptive analytics approach for sustainable cellphone return management
Bibliographic record
Abstract
The rapid turnover of cellphones intensifies electronic waste challenges, demanding data-driven strategies for sustainable management. This study predicts cellphone return rates in Canada by integrating the Hawkins, Best, and Coney consumer behavior model, which captures key psychological and situational drivers of returns, with machine learning algorithms (Random Forest, Extreme Gradient Boosting, and Neural Network). The machine learning analysis achieved predictive accuracy of R 2 = 0 . 9984 , identifying privacy protection (21.8 percent) and incentives (19.4 percent) as the most influential factors. Predicted return volumes were then processed through a hybrid fuzzy rule-based and Monte Carlo simulation framework to classify returned devices by quality: 49.13 percent market-ready, 5.93 percent suitable for parts harvesting, and 44.94 percent requiring recycling. Newer devices (1–2 years) achieved resale rates approximately 80 percent, while four-year-old phones were mostly scrapped. Scenario analysis indicates that increasing return rates by 20 percent could recover over 8.5 million devices annually, prevent 540 million kilograms of CO 2 emissions, avoid 1.9 million kilograms of e-waste, and save energy equivalent to powering 16,500 Canadian homes for a year. Metal recovery from scrapped units could be valued at up to USD 18 million, while refurbishing market-ready phones saves 385,000 metric tons of CO 2 . This study demonstrates stepwise integration of behavioral modeling, machine learning prediction, and hybrid simulation, providing an actionable framework for reverse logistics planning. The findings support strategic decision-making for refurbishment and recycling, highlight substantial environmental and economic benefits, and align with Sustainable Development Goal 12, advancing circular economy practices and sustainable electronic waste management. • Predict cellphone return rates using behavioral data and machine learning. • Model device quality uncertainty with fuzzy logic and Monte Carlo simulation. • Optimize reverse logistics through predictive and prescriptive analytics. • Drive resource recovery and waste reduction with decision support systems. • Support environmental goals by analyzing return behaviors and device conditions.
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 | 0.002 | 0.006 |
| 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 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".