Market area models, such as the Huff model and its extensions, are widely used to estimate regional market shares and customer flows of retail and service locations. Another, now very common, area of application is the analysis of catchment areas, supply structures and the accessibility of healthcare locations. The huff Python package provides a complete workflow for market area analysis, including data import, construction of origin-destination interaction matrices, basic model analysis, parameter estimation from empirical data, calculation of distance or travel time indicators, and map visualization. Additionally, the package provides several methods of spatial accessibility analysis. The package is modular and object-oriented. It is intended for researchers in economic geography, regional economics, spatial planning, marketing, geoinformation science, and health geography. The software is openly available via the [Python Package Index (PyPI)](https://pypi.org/project/huff/); its development and version history are managed in a public [GitHub Repository](https://github.com/geowieland/huff_official) and archived at [Zenodo](https://doi.org/10.5281/zenodo.18639559).
Market area models are used in economic geography, regional economics, spatial planning, geoinformation science, and marketing, enabling the analysis and forecasting of market areas and customer flows for retail and service locations. The classical and most popular approach is the Huff model (Huff 1962(Huff , 1963(Huff , 1961) ) and its numerous derivates and extensions, such as the Multiplicative Competitive Interaction (MCI) Model (Nakanishi andCooper 1974, 1982). Typical research applications include examining the influence of store attributes and transport costs on consumer store choice, forecasting the revenue of new locations, or predicting the impact of new locations on existing ones (De Beule et al. 2014;Fittkau 2004;Li and Liu 2012;Mensing 2018;Oruc and Tihi 2012;Suárez-Vega et al. 2015;Wieland 2015Wieland , 2019)).
In health geography, such models are used to analyse catchment areas with respect to medical practices and hospitals (Bai et al. 2023;Fülop et al. 2011;Jia 2016;Latruwe et al. 2023;Rhein et al. 2025;Wieland 2018), and they are also increasingly being linked to methods for analyzing the supply structure and accessibility of health locations (Liu L 2022;Rauch et al. 2023;Subal J 2021). Moreover, market area models are also applied to other location-related contexts such as airports or recreation facilities (Wang et al. 2022;Wang et al. 2026).
There are several major challenges in model-based market area analyses:
• The calibration of the Huff model based on observed data on consumer behavior and/or store sales is difficult because the model is nonlinear in its weighting parameters (Huff 2003;Wieland 2017). In this context, the MCI model (Nakanishi andCooper 1974, 1982) has been developed as an econometric estimation technique based on a linearization (log-centering transformation). As this approach requires empirical market shares for fitting, it is applied in cases where customer-store interaction data was obtained by surveys or secondary data (Baviera-Puig et al. 2016;Latruwe et al. 2023;Oruc and Tihi 2012;Suárez-Vega et al. 2015;Wieland 2015Wieland , 2019)). Several other researchers developed and used nonlinear iterative fitting approaches, especially when no empirical customer-store interactions are available, but only total sales of the locations investigated (De Beule et al. 2014;Güßefeldt 2002;GH et al. 1972;Li and Liu 2012;Liang et al. 2020;Mensing 2018;Orpana and Lampinen 2003;Wieland 2017). Due to the pronounced sensitivity of market area models to weighting schemes, the availability of multiple calibration approaches is essential in market area analysis.
• Researchers must choose and compare appropriate weighting functions, which may be chosen based on theoretical considerations and may result in substantially different results. Nowadays, for input variables such as travel time, several weighting functions (e.g., power, exponential, logistic) are used, and the model results are compared using goodness-to-fit metrics (Bai et al. 2023;Latruwe et al. 2023;Li and Liu 2012;Orpana and Lampinen 2003). It is, thus, necessary that, within the market area analysis workflow, several weighting functions are available, and that there are options to compare different model specifications based on fit metrics.
• Calculating travel times may be time consuming because these are based on graph theory network analysis and require real street networks (Huff and McCallum 2008). Therefore, market area analysis typically requires GIS (Geographic Information System) support and/or access to an API providing calculations based on input origins and destinations. It is extremely helpful for researchers if they can also complete this part of the market area analysis workflow within the analysis tool.
The huff package for Python v1.8.x essentially provides the following features:
• Data management and preliminary analysis: Users may load customer origins and supply locations from point shapefiles (or CSV, XLSX). At-tributes of customer origins and supply locations (variables, weightings) may be set by the user. The next step is to create an interaction matrix with a built-in function, on the basis of which all implemented models can then be calculated. Within an interaction matrix, transport costs (distance or travel time between customer origins and supply locations) may be calculated with built-in methods.
• Basic Huff model analysis: Given an interaction matrix, users may calculate probabilities and expected customer flows with respect to customer origins, and total market areas of supply locations.
• Parameter estimation based on empirical data: Given empirical data on customer flows, regional market shares, or total sales, users may estimate weighting parameters of market area models. Model parametrization may be undergone using the econometric approach in the MCI model (if regional market shares are available) or by Maximum Likelihood optimization using regional market shares, customer flow
This content is AI-processed based on open access ArXiv data.