Abstract | Purpose – Research suggests that personal motivation is a critical internal driving force that, if harnessed, can significantly improve an operator's productivity rate when working mobile plant and machinery. The purpose of this paper is to investigate the impact of personal motivation upon plant operator productivity (and examine those variables that stimulate personal motivational forces). Design/methodology/approach – To achieve this, an artificial neural network (ANN) was developed. The ANN's topology comprised a multilayer perceptron, with one hidden layer and three output classifications of “good”, “average”, and “poor” (productivity performance). During development of this model, a non-linear dynamic mapping function and metric were used to improve its classification accuracy. The model initially utilised 32 independent (input) variables identified from the literature such as: pay bonuses; relationships between work colleagues; promotion prospects; and job satisfaction. Findings – Subsequent analyses condensed these variables down to the five most significant (i.e. best motivational classifiers of operative productivity), these being: (v2) receipt of payment for overtime, (v11) job promotion potential, (v22) a safe working environment, (v24) variety of work activities, and (v31) availability of flexible work patterns. Model accuracy when employing these most significant predictors was high at 87.67 per cent. By testing on a hold out sample of original data, the developed model was validated as being reliable and robust. Originality/value – The main conclusion of the work is that operators' personal motivation can best be encouraged by paying attention to “personal satisfiers” and “security” aspects, with particular emphasis being given to work flexibility and variety, a safe work environment, and appropriate operator remuneration. By delivering and exploiting these variables, employers can improve plant productivity rates and, as a consequence, company profitability. |
---|