arbiter
JournalsPricingAccount

The Purchase Intention of Green Personal-Care Products: An Artificial Neural Networks Approach

Saveendra Perera & Arfian Zudana

New Zealand Journal of Applied Business Research2025https://doi.org/10.34074/jabr.19103.13article
ABDC C
Weight
0.50

What the paper says

This study explores the use of deep learning (DL) to predict consumer purchase intentions for green personal-care products. Using primary data collected from 110 consumers via online questionnaires, the study applies artificial neural networks (ANNs) to analyse purchasing behaviour, diverging from traditional statistical methods. Through a rigorous optimisation process, the ANN model achieves outstanding performance, with 90% Accuracy, 100% Recall, and F1 and Precision scores of 95%. These results outperform other machine learning models tested, including random forest, support vector machine (SVM), gradient boosting, XGBoost and decision tree, highlighting the ANN’s superior ability to handle complex, non-linear relationships within small datasets. This study demonstrates that deep learning models are highly adaptable to business requirements in the green personal-care sector, whether in traditional retail or online settings, and can be applied effectively to forecast consumer trends regardless of whether the datasets are complex or relatively simple.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.34074/jabr.19103.13

Or copy a formatted citation

@article{saveendra2025,
  title        = {{The Purchase Intention of Green Personal-Care Products: An Artificial Neural Networks Approach}},
  author       = {Saveendra Perera & Arfian Zudana},
  journal      = {New Zealand Journal of Applied Business Research},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.34074/jabr.19103.13},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

The Purchase Intention of Green Personal-Care Products: An Artificial Neural Networks Approach

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.