Improving service use through prediction modelling: a case study of a mathematics support centre

In higher education, student learning support centres are examples of walk-in services with nonstationary demand. For many centres, the major expenditure is tutor wages; thus, optimizing tutor numbers and ensuring value for money in this area are key. In University College Dublin, the mathematics support centre (MSC) has developed a software system, which electronically records the time each student enters the queue, their start time with a tutor and time spent with a tutor. In this paper, we show how data analysis of 25,702 student visits and tutor timetable data, spanning 6 years, is used to identify busy and quiet periods. Prediction modelling is then used to estimate the waiting time for future MSC visitors. Subsequently, we discuss how this is used for staffing optimization, i.e. to ensure there is sufficient coverage for busy times and no resource wastage during quieter periods. The analysis described resulted in the MSC reducing the number of queue abandonments and releasing funds from overstaffed hours to increase opening hours. The methods used are easily adapted for any busy walk-in service, and the code and data referenced are freely available: https://github.com/ehoward1/Math-Support-Centre-.

Bayesian models for prediction of the set-difference in volleyball

We study and develop Bayesian models for the analysis of volleyball match outcomes as recorded by the set-difference. Due to the peculiarity of the outcome variable (set-difference) which takes discrete values from $-3$ to $3$, we cannot consider standard models based on the usual Poisson or binomial assumptions used for other sports such as football/soccer. Hence, the first and foremost challenge was to build models appropriate for the set-difference of each volleyball match. Here we consider two major approaches: (a) an ordered multinomial logistic regression model and (b) a model based on a truncated version of the Skellam distribution. For the first model, we consider the set-difference as an ordinal response variable within the framework of multinomial logistic regression models. Concerning the second model, we adjust the Skellam distribution to account for the volleyball rules. We fit and compare both models with the same covariate structure as in Karlis & Ntzoufras (2003). Both models are fitted, illustrated and compared within Bayesian framework using data from both the regular season and the play-offs of the season 2016/17 of the Greek national men’s volleyball league A1.

Procurement modes for emergency supplies in the presence of disaster and commercial demands

This paper studies alternative procurement modes for emergency supplies in the presence of a public sector and a private supplier. A key feature of such a supply chain is that the private supplier must consider commercial demand in addition to disaster demand. Three procurement modes are analysed: an option mode (OM), an order-before-disaster mode (OBDM) and a procurement-after-disaster mode (PADM). We provide the optimal decisions associated with these three modes. Theoretical results in the OM show that a large order is not always better for the private supplier. From theoretical and numerical comparative analyses, no mode is absolutely superior. For the public sector, there are two thresholds. When the disaster probability is less than the low threshold, the revenues of all procurement modes are the same; when the disaster probability is larger than the high threshold, the OBDM has the highest revenue; otherwise, the OM has the highest revenue. However, for the private supplier, the PADM always has the highest revenue.

Modelling team performance in soccer using tactical features derived from position tracking data

Decision-makers in soccer routinely assess the tactical behaviour of a team and its opponents both during and after the game to optimize performance. Currently, this assessment is typically driven by notational analysis and observation. Therefore, potential high-impact decisions are often made based on limited or even biased information. With the current study, we aimed to quantitatively assess tactical performance by abstracting a set of spatiotemporal features from the general offensive principles of play in soccer using position tracking data, and to train a machine learning classifier to predict match outcome based on these features computed over the full game as well as only parts of the game. Based on the results of these analyses, we describe a proof of concept of a decision support system for coaches and managers. In an analysis of 302 professional Dutch Eredivisie matches, we were able to train a Linear Discriminant Analysis model to predict match outcome with fair to good (74.1%) accuracy with features computed over the full match, and 67.9% accuracy with features computed over only 1/4th of the match. We therefore conclude that using only position tracking data, we can provide valuable feedback to coaches about how their team is executing the various principles of play, and how these principles are contributing to overall performance.

Location flexibility in parcel delivery operations: framework and empirical analysis

In traditional parcel delivery operations, customers determine delivery locations and, hence, the performance of a transporter. We exploit this idea and show that customers can improve the efficiency of a transporter by giving the latter flexibility in choosing the delivery locations. Two possible policies to enable this flexibility are presented and evaluated. The first policy, conceptually similar to roaming vehicle routing, is related to the presence of alternative locations. The second policy is related to the possibility of aggregating/skipping some locations. We show that route optimization behind both policies can be modelled via the well-known generalized travelling salesman problem. Extensive computational experiments with real parcel delivery data are performed to evaluate the potential of the presented policies and to obtain insights for possible implementation in daily practice. The experiments show that under certain conditions, the two proposed policies can lead to 15 to 20% improvement in the route length and in extreme yet realistic cases up to 40 to 50%. Consequently, the concept of flexible delivery locations has potential for practice, especially in densely populated areas.

A stochastic dominance approach to pension-fund selection

This paper contributes to the research on multi-pillar pension systems with main focus on private pension funds (PFs). In this context, the specific objective of this study is to determine which second-pillar private fund is the best for participants in such systems on the basis of their risk profile. Based on the assumptions on utility functions of the participants in a pension scheme, four types of stochastic dominance (SD) relations are considered, specifically first order, second order, third order and SD generated by utility functions with decreasing absolute risk aversion. We conduct an analysis under two distributional assumptions: empirical and stable distribution of returns. Moreover, the investors for which non-dominated funds are the optimal choices are identified. Allowing for diversification, the efficiency of the PFs with respect to several types of SD is tested. Then, the observed behaviour of participants in the last quarter/year is compared to the results of SD analysis. Finally, the identified SD relations are stress-tested using data originating from a period of turmoil. Despite the focus on Lithuanian PFs, the methodology developed in this work can be employed by participants or PF managers in similar markets of other countries.