Allies From Within: I-O Practitioners in Organizations

The focal article (Lapierre et al., 2018) highlights many good suggestions but only briefly mentions partnering with an academically trained internal industrial and organizational (I-O) practitioner. We believe beginning a partnership with a similarly trained ally well-versed through training in academic language and through experience in “business speak” will yield a stronger end result. The appreciation for an internal I-O practitioner should not go overlooked; when an academic partners with the right practitioner in the right environment, the partnership can be mutually beneficial and more rewarding than other options. For instance, recently we collaborated to set up a partnership for scientific discovery and mutual interest that involved 12 teams representing 14 different institutions spanning academe and practice to conduct a machine learning competition. This partnership enabled many academics and practitioners access to a complex organizational dataset in order to contribute to both an organization and the Society for Industrial and Organizational Psychology (SIOP) community (see Putka et al., 2018).

Download Full-text

Predictive modelling of hospital readmission: Evaluation of different preprocessing techniques on machine learning classifiers

Intelligent Data Analysis ◽

10.3233/ida-205468 ◽

2021 ◽

Vol 25 (5) ◽

pp. 1073-1098

Author(s):

Nor Hamizah Miswan ◽

Chee Seng Chan ◽

Chong Guan Ng

Keyword(s):

Machine Learning ◽

Hospital Readmission ◽

Performance Metrics ◽

Predictive Performance ◽

Predictive Modelling ◽

Machine Learning Classifiers ◽

Learning Classifiers ◽

Set Up ◽

The Right ◽

The Impact

Hospital readmission is a major cost for healthcare systems worldwide. If patients with a higher potential of readmission could be identified at the start, existing resources could be used more efficiently, and appropriate plans could be implemented to reduce the risk of readmission. Therefore, it is important to predict the right target patients. Medical data is usually noisy, incomplete, and inconsistent. Hence, before developing a prediction model, it is crucial to efficiently set up the predictive model so that improved predictive performance is achieved. The current study aims to analyse the impact of different preprocessing methods on the performance of different machine learning classifiers. The preprocessing applied by previous hospital readmission studies were compared, and the most common approaches highlighted such as missing value imputation, feature selection, data balancing, and feature scaling. The hyperparameters were selected using Bayesian optimisation. The different preprocessing pipelines were assessed using various performance metrics and computational costs. The results indicated that the preprocessing approaches helped improve the model’s prediction of hospital readmission.

Download Full-text