A neural network solution for forecasting labor demand of drop-in peer tutoring centers with long planning horizons
- PDF / 1,321,110 Bytes
- 22 Pages / 439.37 x 666.142 pts Page_size
- 54 Downloads / 163 Views
A neural network solution for forecasting labor demand of drop-in peer tutoring centers with long planning horizons Rick Brattin 1
& Randall
S. Sexton 1 & Wenqiang Yin 1 & Brittaney Wheatley 1
Received: 2 February 2019 / Accepted: 7 June 2019/ # Springer Science+Business Media, LLC, part of Springer Nature 2019, corrected publication 2019
Abstract Like many other service organizations, drop-in peer tutoring centers often struggle to determine the required number of qualified tutors necessary to meet learner expectations. Service work is largely a response to probabilistic calls for staff action and therefore difficult to forecast with precision. Moreover, forecasting models under long planning horizons often lack the complexity or specificity necessary to accurately predict flexible labor demand due to sparse availability of influential model inputs. This study builds upon the flexible demand literature by exploring the use of neural networks for labor demand forecasting for a drop-in peer tutoring center of a large university. Specifically, this study employs a neural network solution that includes a genetic algorithm to search for optimal solutions using evolutional processes. The proposed forecasting model outperforms traditional smoothing and extrapolation forecasting methods. Keywords Neural network . Genetic algorithm . Labor demand modeling . Long planning
horizon . Labor forecasting
1 Introduction Most colleges and universities offer some form of student tutoring services (Gerlaugh et al. 2007). Drop-in peer tutoring is one such service where students with specific domain knowledge and expertise provide help to other students who need assistance with coursework within that domain (DeFeo et al. 2017). Tutors are often co-located at tutoring centers within a central location such as a library or student center. Students
* Rick Brattin [email protected]
1
Management and Information Technology Department, Missouri State University, Springfield, MO, USA
Education and Information Technologies
who take advantage of tutoring services often experience enhanced learning (Fullmer 2012), improved performance (Drago et al. 2018), greater academic success (Cooper 2010), and are ultimately more likely to graduate (Gallard et al. 2010). With drop-in tutoring, student tutors take direct pedagogical responsibility for creating learning opportunities for student learners (Backer et al. 2016). Assuming tutors hold the requisite knowledge and ability to fulfill these responsibilities, success of an individual learner’s tutoring session is largely dependent upon the extent to which a tutor is available for individualized attention (DeFeo et al. 2017). While learners may need some amount of independent work time during a tutoring session, extended time spent waiting for a tutor leads to frustration and impedes the learning process. Accordingly, success of drop-in peer tutoring programs depends, to a large extent, upon staffing a sufficient number of tutors to cover learner demand. Conversely, overstaffing
Data Loading...
