How Much Data Analytics is Enough? The ROI of Machine Learning Classification and its Application to Requirements Dependency Classification
Bibliographic record
Abstract
Machine Learning (ML) can substantially improve the efficiency and effectiveness of organizations and is widely used for different purposes within Software Engineering. However, the selection and implementation of ML techniques rely almost exclusively on accuracy criteria. Thus, for organizations wishing to realize the benefits of ML investments, this narrow approach ignores crucial considerations around the anticipated costs of the ML activities across the ML lifecycle, while failing to account for the benefits that are likely to accrue from the proposed activity. We present findings for an approach that addresses this gap by enhancing the accuracy criterion with return on investment (ROI) considerations. Specifically, we analyze the performance of the two state-of-the-art ML techniques: Random Forest and Bidirectional Encoder Representations from Transformers (BERT), based on accuracy and ROI for two publicly available data sets. Specifically, we compare decision-making on requirements dependency extraction (i) exclusively based on accuracy and (ii) extended to include ROI analysis. As a result, we propose recommendations for selecting ML classification techniques based on the degree of training data used. Our findings indicate that considering ROI as additional criteria can drastically influence ML selection when compared to decisions based on accuracy as the sole criterion
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 | 0.027 | 0.114 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.005 | 0.010 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 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".