Over the course of two months, we, Clappform has actively designed a data-driven solution for an International Commercial Real Estate (CRE) Company (retail). Our flexible cloud-based platform can help companies to provide them with AI analytics to make their operations more data-driven. For this company, our AI solution is implemented to change their decision-making process to decide on which new stores to introduce based on actual data. Analyses over the trade area for a particular Point of Interest (POI) were made after which a dynamic model is created to help the company in determining what specific stores to approach when there are vacancies. Next to that, our solution provides an overview of which branches or specific stores are underperforming. Creating insight in both will eventually lead to an increase in the market share of the real estate company.
Making use of an agile development process with continuous delivery, together with ongoing feedback and validation, delivers a solution perceived as extremely valuable by the client. By determining the spend potential and analyzing the competition resulting in a dynamic market share, advanced analytics can be converted into real business value for this large international CRE Company.
GeoAnalytics and Competition Analysis
We determined the spend potential of the geographic area based on three pillars: POI, Accessibility, and Competition. The only input required from our client is their POI and assumed competing for CRE. Based on the three factors involved in the GeoAnalytics, it is possible to determine the Spend Potential for the POI and the Spend Potential per branch.
Retail demand depends on the accessibility of households to certain retail centers: the more the distance between two locales increases, the more the amount of activity between those two locales decreases. Hence, in order to predict the market share of retail stores, we introduced an extension to the existing Huff model (Huff, 1962). Besides, using the store size and the Accessibility, a new variable is used: customer reviews. This variable is composed of a stores’ average online rating and its number of ratings. Studies show that 93% of customers state that online reviews influence their decision to make a purchase (Qualtrics, 2020). Hence, the
variable ‘Customer Reviews’ is considered to be very important when defining the attractiveness of a store. Based on these three components, our solution can determine the Relative Attractiveness of any retail asset. This method is extremely interesting for both commercial real estate companies as well as retailers to create valuable insights.
The gravity-based Huff model continues to prove its worth, as the Big Data research by Suhara and others demonstrates (Suhara et al., 2021).
The solution: benchmark performance and vacancy proposals
Knowing the relative attractiveness of all retail assets, it is possible to provide a benchmark of the potential sales against the realized sales. For this specific client, the analyses are performed on branch level. The analyses gave direct insights into how the branch performs against the benchmark and hence knows at glace which branch is underperforming or over-performing. Based on this benchmark performance, the company can decide to shrink the gap towards the full potential and to change a store. Furthermore, the company gets access to a list (per branch) of neighboring retail stores that score high on Attractiveness and hence are expected to perform well within the commercial real estate area. Moreover, an impact analysis per store is conducted to present how the addition of a store would impact the overall sales. This holds similarly for when there is a vacancy within the CRE Area.
Are you curious about how our solution can improve the daily operations of your company? Or how Clappform can help you in other ways?
Do not hesitate to contact us or to request a free demo.
Huff, D. L. (1964). Defining and estimating a trading area. Journal of marketing, 28(3), 34-38.
Suhara, Y., Bahrami, M., Bozkaya, B., & Pentland, A. S. (2021). Validating gravity-based market share models using large-scale transactional data. Big Data.
Kaemingk, D. (2020, October 30). Online reviews statistics to know in 2021. Qualtrics. https://www.qualtrics.com/blog/online-review-stats/
Whatever challenges you have, we are happy to help!
Do not hesitate to contact us or request a free demo.