Research on Prediction of E-commerce Users’ Purchase Behavior Based on Gradient Boosting Decision Tree Model
Bibliographic record
Abstract
Driven by big data, e-commerce platforms have accumulated massive user behavior data, which can be transformed into valuable information after cleaning and feature selection. This study analyzes users’ historical behavioral data on e-commerce platforms, constructs a gradient boosting decision tree prediction model based on user, product, category, and two-by-two interaction behavioral features, and extracts designed feature data from raw CSV data based on Hiv as the prediction basis of the model. At the same time, clustering analysis is performed based on the user’s purchasing behavior (dwell time, browsing frequency) to generate user profiles. The experimental results show that after 7 days, the purchase conversion rate of browsing, collecting, adding to cart and purchasing tends to 0. Therefore, the time window for purchase behavior prediction is chosen to be 7 days. In this paper, the prediction model is only trained to 20 epochs, and the Loss value converges to about 0.14, which shows a good training effect. The model has the best classification performance for user purchase behavior prediction, with precision, recall, and F1 values between 0.91 and 0.97. The clustering algorithm divides the user purchase behavior into four clusters, where cluster class 4 has the best user value. In summary, using the gradient boosting decision tree model, e-commerce platforms can more accurately predict user purchasing behavior, thus improving user experience and platform economic benefits.
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 | 0.005 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".