EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Integrated Artificial Intelligence Framework for Human Resource Management and Marketing Optimization: Predictive Analytics for Organizational Performance

Sreejana Saha, Prof (Dr) Kausik Mukherjee, Dr. S. Jyothirmaye Reddy, Dr. Sachin P. Nagmote, Dr. Nargis Neha, Ved Prakash Tiwari

Computer and Decision Making: An International Journal · 04.11.2026 · 3 (6S) · 2905-2915

DOI: 10.1922/comdem.v3i6s.18829 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer and Decision Making: An International Journal, online erschienen am 04.11.2026. Verfasst von Sreejana Saha und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The potential of combining human resource management (HRM) and marketing analytics for enhancing the predictive power of organizational performance is relatively under-researched. In this study, an artificial intelligence framework was developed and tested to include five HRM indicators and four marketing indicators for predicting a performance index of an organization. 600 records of organizations were generated and quantitatively analysed for five sectors. Descriptive statistics, Pearson correlation, multiple linear regression, and four machine learning algorithms: XGBoost, Decision Tree, Random Forest, and Linear Regression were used. HRM-only, marketing-only and integrated predictor configurations were tested with an 80:20 training:testing ratio and 5-fold cross-validation. The performance of the integrated XGBoost is the best in the test set (R2 = 0.378, MAE = 0.960 and RMSE = 1.972) compared to the top HRM and marketing performance. The marketing conversion rate (r = 0.372) and marketing strategy effectiveness (r = 0.365) had positive correlations with the performance of the organization. When both functional domains were used, the in-sample performance variation was explained by multiple linear regression at 32.7%. According to feature importance analysis, employee engagement, training effectiveness, marketing strategy effectiveness, and marketing conversion rate were influential predictors. Nevertheless, the percentage of observations (83.8%) at the highest level of performance limits interpretation. The results highlight the methodological potential of cross-functional predictive modelling and the importance of validation with data collected separately from the organisation prior to use in operation

Zitieren

APA

Saha, S., Mukherjee, P. D. K., Reddy, D. S. J., Nagmote, D. S. P., Neha, D. N., & Tiwari, V. P. (2026). An Integrated Artificial Intelligence Framework for Human Resource Management and Marketing Optimization: Predictive Analytics for Organizational Performance. Computer and Decision Making: An International Journal, 3(6S), 2905-2915. https://doi.org/10.1922/comdem.v3i6s.18829

Vancouver

Saha S, Mukherjee PDK, Reddy DSJ, Nagmote DSP, Neha DN, Tiwari VP. An Integrated Artificial Intelligence Framework for Human Resource Management and Marketing Optimization: Predictive Analytics for Organizational Performance. Computer and Decision Making: An International Journal. 2026;3(6S):2905-2915. doi:10.1922/comdem.v3i6s.18829

BibTeX
@article{Saha2026,
  author = {Saha, Sreejana and Mukherjee, Prof (Dr) Kausik and Reddy, Dr. S. Jyothirmaye and Nagmote, Dr. Sachin P. and Neha, Dr. Nargis and Tiwari, Ved Prakash},
  title = {An Integrated Artificial Intelligence Framework for Human Resource Management and Marketing Optimization: Predictive Analytics for Organizational Performance},
  journal = {Computer and Decision Making: An International Journal},
  year = {2026},
  volume = {3},
  number = {6S},
  pages = {2905--2915},
  doi = {10.1922/comdem.v3i6s.18829}
}
Kostenlos starten →