报告详情
Intelligent Data Analytics Framework for Organizational Performance Prediction Using Machine Learning and Deep Neural Networks
编号：21
访问权限：仅限参会人
更新：2026-11-10 16:12:03 浏览：10次
Online
摘要
Organizational performance data are noisy, nonlinear, high-dimensional and heterogeneous, as they combine workforce, customer and financial indicators that traditional statistical models analyse in isolation. This paper presents an intelligent data analytics framework that unifies the data science pipeline—data quality assurance, exploratory data analysis (EDA), feature engineering and selection, hyperparameter-optimized machine learning and deep neural network (DNN) modelling, and statistically validated evaluation—into a single decision-support workflow. The framework jointly assesses predictive accuracy, computational efficiency, robustness and statistical consistency. On a 10,000-sample, 24-feature dataset, the proposed model achieved 98.21% training and 96.84% testing accuracy, with precision of 0.965, recall of 0.961, F1-score of 0.963 and ROC-AUC of 0.987, outperforming logistic regression, decision tree, random forest, support vector machine and XGBoost. For regression analytics, it achieved R² = 0.963 with MAE = 0.086 and RMSE = 0.134. Five-fold cross-validation (96.32 ± 0.87%, p < 0.001) confirmed stable generalization, and an average prediction time of 0.012 s per sample supports real-time intelligent analytics for business intelligence and managerial decision-making.
关键词
Data Science; Intelligent Analytics; Predictive Analytics; Machine Learning; Deep Neural Networks; Organizational Performance; Business Intelligence; Decision Support Systems
报告人
Niloy Kumar Bhattacherjee
Dr. B. C. Roy Engine Dept of FMS稿件作者
全部评论
重要日期
-
会议日期
11月20日
2026
至11月22日
2026
-
10月31日 2026
初稿截稿日期
-
11月07日 2026
提前注册日期
-
11月22日 2026
注册截止日期
主办单位
United Societies of Science
承办单位
Pondicherry University
协办单位
IEEE Section
IEEE Madras Section
IEEE Madras Section
联系方式
- ICon INDIA 2026
- ic******@usssociety.org
发表评论