Improving the performance of direct advertising campaigns by applying artificial intelligence techniques

Abstract

Purpose This study aims to enhance the performance of direct marketing advertising campaigns by leveraging artificial intelligence (AI) techniques. With direct marketing increasingly used by banks, insurance companies and retail industries, the study proposes a machine learning-based approach to improve targeting accuracy and campaign efficiency. Design/methodology/approach The proposed methodology integrates the Random Forest classification technique with the Gravity Search Algorithm (GSA) for feature selection. The research is based on the Bank Direct Marketing dataset, utilizing supervised machine learning models to optimize the predictive accuracy of customer responses. The performance of the proposed system is benchmarked against other machine learning models, including Multilayer Perceptron (MLP), Gaussian Naïve Bayes (GNB) and Decision Tree (DT), using accuracy, precision, recall and F1-score as evaluation metrics. The implementation is conducted using Python in the Google Colab environment. Findings The results demonstrate that the hybrid approach of Random Forest and GSA outperforms other traditional machine learning methods in terms of classification accuracy. The proposed model achieved an accuracy of 99.43%, significantly improving prediction performance for direct marketing responses. The integration of GSA effectively reduced data dimensionality by selecting the most relevant features, thereby optimizing computational efficiency and increasing classification precision. Originality/value This study contributes to the field of AI-driven marketing by demonstrating the efficacy of a novel hybrid approach in direct marketing. Unlike traditional marketing strategies that rely on broad audience outreach, this research provides a data-driven methodology for precise customer targeting. The findings have practical implications for marketers and organizations aiming to improve the efficiency and profitability of their direct marketing campaigns. Additionally, this research highlights the role of feature selection optimization in enhancing machine learning performance, providing a framework that can be extended to other domains within predictive analytics.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 8 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.