Document Type : Research Paper

Authors

1 .Sc. Student in GIS engineering. Department of surveying engineering. K. N. Toosi University of Technology. Tehran. Iran

2 Professor of the school of surveying engineering. Department of surveying engineering. K. N. Toosi University of Technology. Tehran. Iran

3 Ph.D. Student in GIS engineering. Department of surveying engineering. K. N. Toosi University of Technology. Tehran. Iran

Abstract

Extended Abstract
Introduction
Selecting a suitable place for a new retail store is a very important decision since new shops cost a lot and new retailers puts themselves at financial risk. Physical location of stores affects the consumer's perception of their first purchase and their subsequent loyalty to the store. Therefore, spatial analysis is very important for retail stores. Site selection for retail stores has always been difficult and the current competitive market has made decision making even more difficult since stores face increased competition and consumers have many options to satisfy their needs. They generally choose a suitable store in their vicinity which provides high quality, cheap, and diverse products. Therefore, markets and especially retailers shall follow an accurate and valid location strategy for new stores. Retail stores have various marketing and customer service strategies. Marketing strategies require a lot of information about different aspects such as customers, shops, competitors, and products. Many marketing strategies only provide information about consumer behavior or customer satisfaction. However, spatial aspects are more important and in fact determine future success of a store. Several methods are used for spatial analysis in retail sector. The present study use a multiplicative interaction model to forecast sales of confectionaries. This can help retailers develop strategies and find an optimal location for their new stores.
 
Materials & Methods
The present study has developed a location-based marketing model for online confectioneries in Tehran which can improve site selection strategies of new confectioneries. This marketing model is based on the multiplicative competitive interaction model (MCI) of the retail location theory. To do so, characteristics attracting customers to confectioneries are determined and related data are collected from the Snappfood online platform through web crawling. ArcMap software is then used to analyze and process the collected data. After data normalization, MCI model is implemented using Python programming language. The model is then calibrated using 80% of the collected data and the ordinary least squares (OLS) method. The model is then evaluated using root mean square error (RMSE) method and the remaining data.
 
Results and Discussion
Mean errors obtained for districts number 1 to 22 of Tehran municipality show high accuracy of the model. Snappfood site lacked any information about districts number 9 and 18 and thus these districts were not considered in the calculations. Depending on the available data, other districts showed different levels of accuracy. Results indicate that district number 22 had the lowest level of accuracy and district 17 had the highest level of accuracy.  In general, this model predicts customer behavior with an error rate of 17.03%. Results of the present study show the probability of purchasing from each confectionery which can be used to map market potential for a new store. This map determines the best place with maximum sale and helps in site selection for new stores based on specific features of the store, competitors and the environment.
 
Conclusions
MCI model predicts sales. From a geomarketing perspective, this model shows that distance between customers and the store and accessibility affect location strategies in new stores. Variables such as pricing and customer satisfaction (scoring) are used to improve the goodness-of- fit of the model. This precise method identifies some key factors to success in a retail strategy. It predicts the probability of purchasing in each district, the number of customers in each store, and distribution of customers in each district. Experts and new retailers can use the results to design various location and sales strategies. Using this model, new retailers in confectionary market can accurately predict their sales before even opening the store and thus protect themselves against possible financial losses. Moreover, this model predicts total sales of different stores and help retailers compare their market shares with those of their competitors. They also can enter features of a new store into the model and find several potential sales strategies. In other words, the model helps determine sales of existing and new shops. In this way, retailers can find an optimum location for their new confectioneries based on the principles of geomarketing.

Keywords

Main Subjects

1- Alarcón, S. (2011). The trade credit in the Spanish agro-food industry. Mediterranean Journal of Economics, Agriculture and Environment (New Medit), 10(2), 51-57.
2- Baviera-Puig, A., Buitrago-Vera, J., & Escriba-Perez, C. (2016). Geomarketing models in supermarket location strategies. Journal of Business Economics and Management, 17(6), 1205-1221.
3- Baviera-Puig, A., Roig-Tierno, N., Buitrago-Vera, J., & Mas-Verdu, F. (2013). Comparing trade areas of technology centres using ‘Geographical Information Systems’. The Service Industries Journal, 33(7-8), 789-801.
4- BE, Ó. G. (2001). Modelización LOGIT de la selección de establecimiento minorista: Fundamentos teóri cos. Esic market.
5- Bekti, R., Pratiwi, N., & Jatipaningrum, M. (2018). Multiplicative Competition Interaction Model to obtained Retail Consumer Choice based on Spatial Analysis. E&ES, 187(1), 012041.
6- Berman, B., & Evans, J. R. (2018). Retail Management a strategic approach: Pearson.
7- Cliquet, G. (1995). Implementing a subjective MCI model: An application to the furniture market. European Journal of Operational Research, 84(2), 279-291.
8- Gonzalez-Benito, O. (2005). Spatial competitive interaction of retail store formats: modeling proposal and empirical results. Journal of Business Research, 58(4), 457-466.
9- Huff, D., & McCALLUM, B. M. (2008). Calibrating the huff model using ArcGIS business analyst. ESRI White Paper.
10- Huff, D. L. (1963). A probabilistic analysis of shopping center trade areas. Land economics, 39(1), 81-90.
11- Huff, D. L. (1964). Defining and estimating a trading area. Journal of marketing, 28(3), 34-38.
12- Kim, H., & Choi, B. (2013). The influence of customer experience quality on customers’ behavioral intentions. Services Marketing Quarterly, 34(4), 322-338.
13- Kubis, A., & Hartmann, M. (2007). Analysis of location of large-area shopping centres. A probabilistic Gravity Model for the Halle–Leipzig area. Jahrbuch für Regionalwissenschaft, 27(1), 43-57.
14- Li, Y., & Liu, L. (2012). Assessing the impact of retail location on store performance: A comparison of Wal-Mart and Kmart stores in Cincinnati. Applied Geography, 32(2), 591-600.
15- Liu, T. (2012). Combining GIS and the Huff Model to Analyze Suitable Locations for a New Asian Supermarket in the Minneapolis and St. Paul, Minnesota USA. Papers in Resource Analysis, 14(8).
16- Luce, R. D. (2012). Individual choice behavior: A theoretical analysis: Courier Corporation.
17- Mahajan, V., Jain, A. K., & Ratchford, B. T. (1978). Use of Binary attributes in the multiplicative competitive interactive choice model. The Journal of Consumer Research, 5(3), 210-215.
18- Marinov, M., & Czamanski, D. (2012). Normative issues in the organization of modern retailers in Israel. GeoJournal, 77(3), 383-398.
19- Merino, M., & Ramirez-Nafarrate, A. (2016). Estimation of retail sales under competitive location in Mexico. Journal of Business Research, 69(2), 445-451.
20- Mitchell, V. W., & McGoldrick, P. J. (1994). The Role of Geodemographics in Segmenting and Targeting Consumer Markets. European Journal of marketing.
21- Nakanishi, M., & Cooper, L. G. (1974). Parameter estimation for a multiplicative competitive interaction model—least squares approach. Journal of marketing research, 11(3), 303-311.
22- Nakanishi, M., & Cooper, L. G. (1982). Simplified estimation procedures for MCI models. Marketing Science, 1(3), 314-322.
23- Orpana, T., & Lampinen, J. (2003). Building spatial choice models from aggregate data. Journal of Regional Science, 43(2), 319-348.
24- Prayag, G., Landré, M., & Ryan, C. (2012). Restaurant location in Hamilton, New Zealand: clustering patterns from 1996 to 2008. International Journal of Contemporary Hospitality Management.
25- Reynolds, J., & Wood, S. (2010). Location decision making in retail firms: evolution and challenge. International Journal of Retail & Distribution Management.
26- Shahbazi, H., Taghvaee, S., Hosseini, V., & Afshin, H. (2016). A GIS based emission inventory development for Tehran. Urban Climate, 17, 216-229.
27- Vega, R. S., Acuna, J. L. G., & Díaz, M. R. (2015). Spatial analysis of consumer behavior in a food products market. Theoretical and Empirical Researches in Urban Management, 10(1), 25-42.
28- Wieland, T. (2017). Market Area Analysis for Retail and Service Locations with MCI. R J., 9(1), 298.
29- Wieland, T. (2018a). Competitive locations of grocery stores in the local supply context-The case of the urban district Freiburg-Haslach. European Journal of Geography, 9(3), 98-115.
30- Wieland, T. (2018b). A Hurdle Model Approach of Store Choice and Market Area Analysis in Grocery Retailing. Papers in Applied Geography, 4(4), 370-