PRMNBR: Personalized Recommendation Model for Next Basket Recommendation Using User’s Long-Term Preference, Short-Term Preference, and Repetition Behaviour
Bibliographic record
Abstract
Next Basket Recommendation (NBR) tries to recommend items in a user's coming basket by understanding the user's characteristics from the past baskets of the user.The existing deep learning models for recommendation system (RS) are formulated by combining the long-term and short-term preferences of the user successfully.Recent statistical-based models highlight the importance of repeat purchase behavior, especially in the E-commerce industry, as most customer repeatedly purchases items.Including repeat behaviour dynamics can lead to a certain degree of improvement in the deep learning-based NBR models, as shown in a few recent statistical-based works.In this paper, we introduced a mechanism to extract the user's repetition behaviour along with the user's long-term preferences and short-term preferences.To capture the repetition behavior of the user, we introduced the encoded user's baskets as Repeat Aware Baskets, and to extract the correlation between items, we used a Correlation Sensitive Basket.Further, separate embedding is generated with respect to Repeat Aware and Correlation Sensitive Baskets.These embedding are fed parallel to two layered Long-Short Term Memory architecture for analyzing short-term preference.To evaluate the performance of the proposed model, we experimented on two data sets.Our proposed algorithm outperformed various recently developed models over various performance metrics.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.004 |
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".