John Wilson is a professor in management science at the Ivey Business School.
-
Murray, L. L.; Wilson, J. G.; Rodrigues, F.; Zaric, G. S., 2023, "Forecasting ICU Census by Combining Time Series and Survival Models", Critical Care Explorations, May 5(5)
Abstract: OBJECTIVES: Capacity planning of ICUs is essential for effective management of health safety, quality of patient care, and the allocation of ICU resources. Whereas ICU length of stay (LOS) may be estimated using patient information such as severity of illness scoring systems, ICU census is impacted by both patient LOS and arrival patterns. We set out to develop and evaluate an ICU census forecasting algorithm using the Multiple Organ Dysfunction Score (MODS) and the Nine Equivalents of Nursing Manpower Use Score (NEMS) for capacity planning purposes. DESIGN: Retrospective observational study. SETTING: We developed the algorithm using data from the Medical-Surgical ICU (MSICU) at University Hospital, London, Canada and validated using data from the Critical Care Trauma Centre (CCTC) at Victoria Hospital, London, Canada. PATIENTS: Adult patient admissions (7,434) to the MSICU and (9,075) to the CCTC from 2015 to 2021. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We developed an Autoregressive integrated moving average time series model that forecasts patients arriving in the ICU and a survival model using MODS, NEMS, and other factors to estimate patient LOS. The models were combined to create an algorithm that forecasts ICU census for planning horizons ranging from 1 to 7 days. We evaluated the algorithm quality using several fit metrics. The root mean squared error ranged from 2.055 to 2.890 beds/d and the mean absolute percentage error from 9.4% to 13.2%. We show that this forecasting algorithm provides a better fit when compared with a moving average or a time series model that directly forecasts ICU census. Additionally, we evaluated the performance of the algorithm using data during the global COVID-19 pandemic and found that the error of the forecasts increased proportionally with the number of COVID-19 patients in the ICU. CONCLUSIONS: It is possible to develop accurate tools to forecast ICU census. This type of algorithm may be important to clinicians and managers when planning ICU capacity as well as staffing and surgical demand planning over a short time horizon.
Link(s) to publication:
https://journals.lww.com/ccejournal/fulltext/2023/05000/forecasting_icu_census_by_combining_time_series.8.aspx
http://dx.doi.org/10.1097/CCE.0000000000000912
-
Murray, L. L.; Wilson, J. G., 2021, "Generating data sets for teaching the importance of regression analysis", Decision Sciences Journal of Innovative Education, April 19(2): 157 - 166.
Abstract: Summary statistics and data visualizations are often used to explore data and draw preliminary conclusions. Although valuable, these tools do not always reveal the underlying patterns and trends in the data and can sometimes be misleading. We describe an approach for teaching the need for more advanced statistical analysis using multiple linear regression. Our approach is based on using a method we developed for generating alternative multivariate data sets where all the variables (both independent and dependent) have the same summary statistics. However, we can deliberately change the statistical significance of one (or more) of the independent variables in the regression to illustrate why it is important to go beyond simple descriptive measures and examine inferential statistics on the inherent relationships in the data. Implementation of this methodology is provided in the R statistical programming language and an add-in for Excel spreadsheets.
Link(s) to publication:
http://dx.doi.org/10.1111/dsji.12233
-
Wilson, J. G.; Chen, J., 2018, "On the optimality of coupon books", Annals of Operations Research, September 268(1-2): 405 - 423.
Abstract: Our research was motivated by the challenge that a discount airline can set prices below traditional levels. One possible response for the traditional airline is to offer a book of coupons at a fixed price, in an attempt to retain or even increase market share. Offering coupon books is a way to induce changes in customer buying practices. Here we assume that each customer acts strategically in deciding whether or not to switch airlines and whether to buy the coupon book or the regular tickets. Other than price, the number of coupons in the book provides a way to segment the market. Airlines usually have data on circumstances where no coupon books were offered, but they generally do not have the luxury of experimenting by offering coupon books and gauging the response. The focus for this work is therefore: using only the data that is currently available (from the non-coupon case), are there key indicators that can help an airline decide whether or not to offer coupon books? We demonstrate that the crucial factor is the company’s current market share, and we show how to establish a threshold market share above which coupon books should not be offered. This becomes useful when advising a manager on a course of action, as the decision can be based on knowledge of current market share and beliefs about future market share. We show that there can be a broad region in which a manager can tolerate the give and take involved in behavioral and group decision making.
Link(s) to publication:
https://doi.org/10.1007/s10479-017-2512-5
-
Maclean, K.; Wilson, J. G.; Krishnamoorthy, S., 2017, "Pricing of excess inventory on Groupon", International Journal of Revenue Management, May 10(1): 52 - 74.
Abstract: We consider the problem faced by a business that is considering using the Groupon platform to sell excess inventory. We discuss how demand functions can be derived using management knowledge. Then, using a single period model where excess inventory is exogenous, we show that the decision to use Groupon and the price to set on that channel depend on two parameters: the relative price sensitivity of Groupon customers as compared to the retailer's regular customers and the relative size of the Groupon market as compared to the regular market. Under a two-period model, when initial inventory is a decision, we show optimal inventory quantities. Our two-period model suggests that managers may plan on using Groupon and order inventory accordingly. We discuss the implications on third party channels as well as retail managers.
Link(s) to publication:
https://doi.org/10.1504/IJRM.2017.084152
-
Wilson, J. G., 2016, "Jointly Optimising Prices for Primary and Multiple Ancillary Products", IFAC-PapersOnLine, June 49(12): 267 - 270.
Abstract: There are many industrial applications where attempts are made to sell ancillary products or service with a primary item For instance, a warranty is often offered as an ancillary product to those who buy the television sets (the primary item). This has become even more important in the airline industry where ancillary products such as baggage fees have become very important to the financial health of the industry. In this paper, the question of what price to charge for the primary and ancillary products will be investigated. (C) 2016, IFAC (Informational rederation of Automatic Control) Hosting Elsevier Ltd. All rights reserved.
Link(s) to publication:
http://dx.doi.org/10.1016/j.ifacol.2016.07.615
-
Odegaard, F.; Wilson, J. G., 2016, "Dynamic Pricing of Primary Products and Ancillary Services", European Journal of Operational Research, June 251(2): 586 - 599.
Abstract: Motivated by the growing prevalence for airlines to charge for checked baggage, this paper studies pricing of primary products and ancillary services. We consider a single seller with a fixed capacity or inventory of primary products that simultaneously makes an ancillary service available, e.g. a single-leg flight and checked baggage service. The seller seeks to maximize total expected revenue by dynamically setting prices on both the primary product and the ancillary service. In each period, a random number of customers arrive each of whom may belong to one of three groups: those that only want the primary products, those that would buy the ancillary service if the price is right, and those that only purchase a primary product together with the ancillary service. A multi-period dynamic pricing model is presented with computational complexity only of order equal to the number of periods. For certain distributions, close to analytical results can be obtained from which structural insights may be gleaned.
Link(s) to publication:
http://dx.doi.org/10.1016/j.ejor.2015.11.026
-
Wilson, J. G.; Anderson, C. K., 2015, "Joint Pricing and Inventory Decisions", IFAC-PapersOnLine, May 48(3): 238 - 241.
Abstract: The problem of assigning inventory to different pricing levels is considered. The problem is motivates by hoteliers assigning rooms to an opaque discounter. It can also be thought of as assigning seats and fares to two different classes where the cheaper class sells out first. The approach can be used for retail promotions such as all items 20% of during the first hour of business. While the operations literature has looked extensively at joint pricing and inventory decisions in the single product setting, we extend the literature and provide closed form solutions to the multiproduct setting where demand across the products is dependent and the products share resources
Link(s) to publication:
http://dx.doi.org/10.1016/j.ifacol.2015.06.087
-
Anderson, C. K.; Odegaard, F.; Wilson, J. G., 2015, "A newsvendor approach to inventory and pricing decisions in NYOP channels", Journal of Revenue and Pricing Management, February 14(1): 3 - 15.
Abstract: In opaque selling certain characteristics of the product or service are hidden from the consumer until after purchase, transforming a differentiated good into somewhat of a commodity. Opaque selling has become popular in travel service pricing as it allows firms to sell their differentiated products at higher prices to regular brand loyal customers while simultaneously selling to non-loyal customers at discounted prices. At its simplest level, the process can be regarded as a Newsvendor problem where a supplier has to make both pricing and quantity allocation decisions for a perishable good or service. As the originator of opaque selling, Priceline.com provides unique data to sellers that allows them to better utilize their opaque selling mechanism. Recently Priceline has made some changes to their mechanism that have potential impacts on how firms set prices and control inventory within the channel. In this framework, the problem has the characteristics of Newsvendor problems with multiple price points. In this article, we develop optimal pricing and inventory policies for a seller releasing inventory to an opaque sales channel. Furthermore, we investigate the impacts of Priceline’s changes upon optimal prices and inventory allocation policies. The model is empirically illustrated using Priceline data for a 3.5 star hotel.
Link(s) to publication:
http://dx.doi.org/10.1057/rpm.2014.32
-
Wilson, J. G.; Sorochuk, C., 2013, "The Newsvendor Problem with Pricing and Secondary Revenues", Journal of Applied Business and Economics, June 14(4): 11 - 23.
Abstract: Many industries (e.g. hotel, rental car, cruise line and airline companies) consider secondary revenues a major source of profitability. In 2010, for instance, the five largest airlines in the United States received a total of 2.7 billion in revenue from baggage fees alone. Some casinos give away rooms since secondary activities are so profitable. Secondary revenues cannot occur without the purchase of a primary item. The price of the primary item is crucial. We consider optimal inventory levels and prices for primary items. We allow the secondary revenue to depend on the price of the primary item.
-
Wilson, J. G.; MacDonald, L.; Anderson, C. K., 2011, "A Comparison of Different Models for Joint Inventory-Pricing Decision", Journal of Revenue and Pricing Management, December 10(6): 528 - 544.
Abstract: Pricing and inventory research often focuses on stylized models to illustrate pricing and ordering decision dynamics. Although decision insight is useful, the individual retailer faces tougher decisions on actually modeling demand. In an effort to understand the impact of demand modeling choices on inventory and pricing decisions, we evaluated different price-dependent demand models and the resulting profit produced through their implementation. To avoid complications created by other demand drivers, for example promotional and advertising activities, we illustrate the impacts with data from a name-your-price retailer selling a commoditized product where price is the key driver. As our data are provided by a third-party intermediary, we capture all demand requests in the marketplace versus obtaining sales only from a single retailer, enabling us to truly evaluate the profit impacts of price modeling decisions. Our choice of data set also obviates the censoring issues often associated with the evaluation of inventory and pricing decisions. A goal of the article is to provide a practitioner with helpful advice on choosing a modeling approach for joint pricing and inventory decisions.
Link(s) to publication:
http://dx.doi.org/10.1057/rpm.2011.32
-
Anderson, C. K.; Wilson, J. G., 2011, "Name-Your-Own Price Auction Mechanisms Modeling and Future Implications", Journal of Revenue and Pricing Management, January 10(1): 32 - 39.
Abstract: A popular method for selling excess inventory over the Internet is via a Name-Your-Own Price auction, where the bidder bids on an item and the seller immediately decides on whether or not to accept the bid. The analytical modeling of such auctions is still in its infancy. A number of papers have appeared over the last few years making various assumptions about buyers and sellers. The intent of this article is to carefully delineate the various assumptions and modeling approaches and, consequently, suggest avenues for further research.
Link(s) to publication:
http://dx.doi.org/10.1057/rpm.2010.46
-
Sorochuk, C.; Wilson, J. G., 2011, "The Newsvendor Problem with Pricing, a Dual Price-Quantity Pairs Model", Journal of Accounting and Finance, January 11(1): 31 - 39.
-
Wilson, J. G.; Sorochuk, C., 2009, "Optimal Pricing and Inventory Decisions when Individual Customer Preferences are Explicitly Modeled", International Journal of Revenue Management, December 2(3): 119 - 132.
Abstract: We approach the newsvendor with pricing problem as a practitioner who must model demand as a function of price. Previous work required strong assumptions about demand curves, making practical implementation of results problematical. Instead, we assume that customers have reservation prices which can be determined through standard marketingstatistical techniques. We then derive a demand curve and investigate the ramifications for setting the optimal price and quantity. We demonstrate that a practitioner often need only estimate some intuitive quantities of the possible consumers. Using our approach, it is possible to infer what assumptions impose on a model of individual consumer behaviour.
-
Anderson, C. K.; Wilson, J. G.; Zhang, G., 2008, "Case: Bidding on Priceline", INFORMS Transactions on Education, September 8(1): 35 - 36.
Abstract: Priceline.com is an Internet-based corporation offering services (airline tickets, hotel rooms, rental cars, and home mortgages) with the option for consumers to dictate prices. Priceline's original success stemmed from its innovative 'name your price' approach whereby consumers bid for service with Priceline to find a willing provider at the bid price. Consumers are only allowed to bid once on a service so they must be strategic in bidding---bid too low and potentially lose out on service, bid too high and overpay for the service. While they are only allowed to bid once per product, bidders can slightly alter their service and potentially re-bid in an effort to get new information (from failed attempts)-such alterations may include a different class of hotel (3 star versus 4), a flight with 1 stop versus direct, or (as in the case below) a different class (economy versus luxury) of rental car. The case is designed to cover a broad range of topics while introducing students to auctions. The case teaches strategic bidding while covering probability, decision analysis, and integer programming. The case has had great success at the undergraduate and MBA levels as students enjoy the setting, are familiar with Priceline, and immediately see an everyday use of management science.
-
Wilson, J. G.; Zhang, G., 2008, "Optimal Design of a Name-Your-Own-Price Channel when Customers Behave Strategically", Journal of Revenue and Pricing Management, September 7(3): 281 - 290.
Abstract: A retailer places a certain product (eg compact rental cars) for sale on the internet. Customers are invited to 'name-their-own price' for the product. The retailer will accept a given bid x with probability equal to p(.). It is assumed that customers know the function p(.) and will place bids that maximise their individual expected profits. Knowing that customers will behave this way, the retailer wants to choose the function p(.) that maximises the retailer's expected profit. We demonstrate that there is an explicit [varepsilon-optimal solution to this problem.
For more publications please see our Research Database