Lisbon, September 19, 2023: Casafari, a leading European platform for real estate data, today announces the acquisition of Targomo, an expert in location intelligence. This move works to strengthen Casafari’s capabilities in the real estate and proptech market via the integration of comprehensive AI-based location analysis.  

Berlin-based Targomo has developed AI-based software which provides assessments of quality of locations for a range of purposes, working to model characteristics and forecast predicted performance. The intuitive SaaS tool enables companies to find the best locations for their needs, optimise entire networks, and increase overall profitability. Targomo offers a powerful API suite with access to comprehensive location-based data and reachability information. The transaction unlocks obvious synergies by enhancing Real Estate Search and Analysis with Location Intelligence on one side, and Powering Targomo LOOP with complete Real Estate Data on the other side.  

Targomo clients will benefit from direct access to CASAFARI’s proprietary real estate database, the most complete and accurate data on all properties in Europe. CASAFARI clients will benefit from complete real estate market information enriched by location intelligence. The agreement addresses a crucial pain point for customers in both the commercial and residential real estate sectors, providing businesses a competitive advantage via access to the most up-to-date and complete data on the market. The market insights enabled by real estate data and AI-powered location intelligence will accelerate deals for all participants of the real estate transaction. 

Targomo has received around 10 million euros in total with the last Series A round in 2020 to support the development of Targomo’s cutting-edge technology. As a part of the acquisition, Targomo’s existing team continues to work in key strategic roles from their Berlin headquarters. 

The agreement between Targomo and CASAFARI will deliver significant benefits for both companies, with Targomo expanding its customer base in CASAFARI’s core markets (Spain, Portugal, France, and Italy), while CASAFARI gaining access to Targomo’s enriched socio-demographic information and location intelligence for its more than 50,000 real estate customers in Southern Europe. 

CASAFARI and Targomo are committed to providing businesses with the tools they need to succeed in today’s data-driven world. By combining CASAFARI’s real estate expertise with Targomo’s location intelligence, this partnership will create a powerful solution that helps businesses and investors make informed decisions about where to invest and grow, whether they are in real estate, retail, finance, or any other sector that relies on data for success. 

About Targomo

Targomo helps retailers and restaurant brands make better and faster location decisions. It offers an analytics platform with 400+ high quality data sets for 25+ countries and develops customised Geo AI prediction models that enable businesses to forecast relevant sales metrics for any potential location – instantly. The location intelligence specialist has been awarded as one of Europe’s Top 5 Deep Tech scaleups and serves customers in more than 20 countries, including McDonald’s Germany, RSG (McFit, Gold’s Gym) and Søstrene Grene.

About Casafari

CASAFARI is a leading real estate network that connects 50,000 professionals through its innovative data and collaboration tools. With proprietary technology to index, aggregate, and analyse 310 million listings from 30,000 sources, CASAFARI builds property history, property sourcing search, CMA, market analytics, market reports, APIs and CRM to serve such clients as Cerberus, Kronos, Vanguard, Masteos, Casavo, Sotheby’s International Realty, Coldwell Banker, Century 21, Savills, JLL, Engel & Völkers, Keller Williams among others on the real estate market.

Note: CASAFARI is an exclusively B2B real estate data platform,  serving real estate professionals and not a real estate agency. 

Climate protection initiatives can be launched by planning them down to the last detail from the outset, or they can be tested as a pilot project in a test environment in order to quickly obtain results from practical experience. To support the second approach, HafenCity University (HCU) Hamburg has developed ANN RADAR (A New Normal). Funded by the ICLEI Action Fund, the project helps the city of Hamburg identify suitable spaces and districts for testing sustainable energy innovations, leveraging Targomo’s API services.

“ANN RADAR provides a data-driven decision-making basis for finding testbeds for climate protection measures,” explains Kay Hartkopf, senior researcher at HCU Hamburg who is leading the development of ANN RADAR. “The more suitable the areas are for testing, the faster we can gather knowledge and ensure that the measures are implemented on a broad scale.”

The project identified three core topics of sustainable urban development for which the ANN RADAR will select test areas: Mobility, Solar & Photovoltaic, and Energy Efficiency. TargomoAPI is used in particular for scenarios around the topic of mobility. Here, the focus is on planning local logistical mobility centres, as envisaged, for example, in the HCU’s MOVE 21 project. MOVE21 is an innovation project funded by the European Commission that aims to transform European cities and their surroundings into intelligent, emission-free hubs for mobility and logistics.

“Targomo is a great support for us, as we can use the API to answer relevant questions on mobility, accessibility and supply quality and visualise them on maps,” says Kay Hartkopf. “We particularly benefit from the fast data processing and the wide range of customisation options that enable us to perform complex analyses.”

ANN RADAR is designed as a process support (moderated process for selecting urban testbeds) and was inspired by “A New Normal” in Melbourne, Australia, which is developing prototypes and pilot projects related to a sustainable Melbourne 2030. It collects indicators to find the most suitable urban areas for selected climate protection measures. It also takes into account local climate strategies and available environmental data to support evidence-based decision-making. As different data sources can be quickly integrated and combinations of data sets can be explored, it also promotes stakeholder participation and enables the development of specific perspectives for these target groups.

Building on the experience gained, it is planned to expand ANN RADAR in the future to include further data layers (e.g. environmental data, heat islands, urban green, real-time mobility data) and functions for the exploration of specific project scenarios.It is currently available for HCU projects.

Analyses of individual locations and their catchment areas are crucial for making data-driven location decisions, but they often overlook an important aspect – the impact of neighboring shops and competitors. To address this issue, network analyses can be performed to better understand the interactions and gravitational attraction between shops.

Targomo’s Statistics Context API has some deep functionality, one of which is an implementation of our multigraph API with statistics datasets as the aggregation geometries. This allows us to run complex aggregations – in this case the Huff model. This allows us to calculate the likelihood of certain demographic groups coming to a location and the likelihood of a location attracting the revenue potential of a region.

In the example below, we are simulating two store networks: our network (black pins), and the competition: (gray pins). For simplicity’s sake, we are assuming that all locations are equally attractive, aside from distance.

The color of the statistics cells represent how likely the inhabitants at that location are to visit a store in our network. Since the cells contain population data, we can therefore multiply the likelihood by the statistic value to get a total potential visitor count.

How it works:

One important outcome of network analyses is the determination of how demand is distributed among existing locations, including both in-network and competition. Gravitational models, which measure the force-based interactions between nodes in a network, are often used to determine this distribution. In the context of retail consumer analytics, the concept of gravity refers to the attractivity of a retail location to potential customers.

By utilizing network analyses and gravitational models, we can gain valuable insights into customer behavior and make informed decisions about location strategies. Understanding the interplay between neighboring shops and the attractivity of each location can help businesses optimize their presence and stay competitive in today’s market.

The Huff model (or Huff’s model), developed by David B. Huff in 1963, builds on the gravitational model. It is a widely used tool for predicting the probability of a visitor to a site as a function of the distance of the site, its relative attractiveness (compared with other sites), and the relative attractiveness of alternatives. In other words, it predicts the likelihood of people preferring one location over another based on factors such as distance, attractiveness and competition.

In an emergency situation, quick response times are crucial. They help emergency workers minimise the risk of further injury or damage, and increase the chances of a positive outcome of the incident for those involved. Whether in accidents, emergency medical services or fires, a large part of this response time is determined by the travel of emergency vehicles. However, roads can suddenly become impassable due to sudden events such as environmental factors or protesters blocking roads.

To enable developers and planners to improve their responses in emergency situations, Targomo has released a new feature. The “Polygon Exclusion” feature makes it possible to exclude specific areas (polygons) from the routing at any time. This could be necessary, for example, if there is a road blockage, an area is affected by a fire or a flood causes roads or bridges to become inaccessible – EMS providers can adjust their analyses on-the-fly, without waiting for road data updates. 

However, the new feature not only improves rapid response in emergency situations, but also enables better planning in the event of disasters. Combined with other Targomo data services, emergency planners are able to see how many people need to be cared for or evacuated within a prescribed minimum time. If a bridge washed out, how many people would be inaccessible and need to be cared for? What countermeasures should be initiated? Are the existing locations of, for example, the police or fire brigade sufficient to provide adequate care, or are more locations needed?  

“The new feature can be used to answer a variety of safety-related questions,” says Adam Roberts, product manager of TargomoAPI. “We developed the feature explicitly according to the wishes and requirements of our rapid response customers, as theywere unable to find such a feature anywhere in the world. The feature is now actively deployed in countries on several continents, including the US, Norway, and Germany, and we hope this will help many people in emergency situations faster and better.”

Targomo provides high-performance developer tools for building state-of-the-art geospatial analytics tools, improving location search and personalising the user experience. The API portfolio is characterised by fast processing and very precise routing and built-in customisation options that allow developers to adapt their solution to all individual scenarios 

When expanding a business, especially opening a new store in a new region, the biggest questions to be answered is whether the store can be expected to perform well and how much revenue it could potentially generate. Revenue prediction is very important in supporting site selection and decision making for ensuring a successful expansion, and there are several approaches that aim to deliver accurate forecasts.

Two machine learning algorithms that are commonly used to predict revenue are Random Forest and XGBoost. In this revenue prediction case study we compare the results from both these popular models with the results generated by Targomo’s Geo AI model. Geo AI is a location-based model, aiming for a better understanding and evaluation of the characteristics of the shop location.

The basis for this case study is the publicly available data for liquor sales data in the US-state Iowa. For the prediction, we selected the brand Hy-Vee and treated liquor sales of other brands as competitor data.

Who is Hy-Vee? Hy-Vee is an employee-owned chain of supermarkets, mostly located in the Midwestern and Southern US. Its headquarters is in West Des Moines, Iowa. Hy-Vee has over 285 locations in 8 states in the US, including among others Iowa, Illinois, Missouri. As all data of liquor sales in Iowa, Hy-Vee’s data was publicly available.

The three models Random Forest, XGBoost, and Targomo’s Geo AI were used for the revenue prediction. The Random Forest and XGBoost models are often applied in prediction as their advantage is their efficiency in dealing with high dimensional data. In addition, both random forest and XGBoost are decision-tree-based models and easy to work with – there’s no need to normalize data and Python/R packages are readily available to use. It can create a relative robust model even with outliers and missing values. The drawbacks, however, are also obvious: Potential over fitting issues and low interpretability.

Geo AI is a locational-based method. The foundations of the model were developed as part of a research project conducted by Targomo in collaboration with the Hasso-Plattner-Institut and funded by the Deutsches Zentrum für Luft- und Raumfahrt.

One major component of Geo AI is a gravitational model. It follows the idea of Newton’s law of gravitation applying the concept to market models. According to Newton’s law of gravitation, high masses (attractiveness in market models) and short distance lead to strong attraction. The attractiveness is measured by the store’s characteristics and environment. These factors could be characteristics like store size, parking space, product range, or location factors like complementary shops, competitors or other points of interest close by.

In our model, these factors are called attraction strength. The distance, in Geo AI, is calculated based on travel time with catchment areas defined by travel time and travel mode including car, bike, public transit, and walking. A travel-time-based catchment area provides a more accurate and realistic assessment of population than more naïve distance-based catchments.

To begin, Targomo’s data team first needed to compile data from various sources to calculate the general demand and attractiveness of stores:

Data cleaning is one of the first and most important steps in modelling as cleaned data is the foundation of a correct model and its output. The process of data cleaning involves detecting inaccurate, incomplete, and duplicated records, and then fixing or removing them.

Furthermore, stores with extreme high or low annual sales have also been carefully reviewed, noting that some were beverage and liquor retailers. Since these stores cater to different customer groups – namely other stores – these outliers were removed from the data set. Casinos, hotels, inns, and distilleries were also removed.

In countless iterations, the Geo AI engine is fed with data to continuously learn which data composition represents Hy-Vee’s store performance.

The training consists of two main components:

There are two relevant values measured during the learning process that indicate the prediction quality: The training error and the testing error.

When it comes to prediction results, the testing error can be considered to be more meaningful because it gives us an idea of how well the model will perform on new, unseen data – like the address of a potential new location for a shop opening. A low training error is a precondition for, but alone not a sufficient indicator of a successful project.

In our revenue prediction projects we usually go through two phases during the model training:

The table compares the model accuracy and detected success drivers of three liquor sales prediction models for Hy-Vee stores. The training error of Geo AI model is 16% and the testing error is 19.8%, while the testing errors of Random Forest model and XGBoost model are 38.1% and 30% respectively. Compared with the two commonly used models, Geo AI yields the highest model accuracy.

The identified attributes in the Random Forest and XGBoost models are rather limited and are restricted to the number of items, the number of visitors, and one or two socio-demographic attributes.

In contrast, the Geo AI model consists of a wide range of features, including among others store features (item count, shop type), surrounding environment (footfall at the location), and socio-demographic characteristics of potential customers. Item count, indicating the variety of liquors offered in store, shop type, and shopping footfall in the close neighbourhood are used to measure store attractivity in the gravitational model.

The scatter plot of the Geo AI output: The x-axis is the actual liquor sales, and the y-axis is the predicted liquor sales. The dots are nicely distributed along the diagonal line, which indicates a good prediction performance of Targomo’s Geo AI.

Income is a major driver of the liquor sales in Hy-Vee shops. 25.8% of the sales are from households with income less than 40,000$, and 14.5% are from households with incomes greater than 150,000$. Many studies have found that low-income individuals are at higher risk of engaging in heavy and hazardous drinking, and higher income is associated with a higher frequency of light drinking.

In addition to income, certain occupations have also a positive influence on liquor sales in Hy-Vee stores in Iowa. The results show that people working in construction, wholesale trade, and art industries as well as those who are self-employed are strong drivers. According to Statista, the top 5 high alcohol consumption (15 or more alcoholic drinks per week) occupations in the US 2016 are construction or mining, installation or repair, farming, fishing, or forestry, manufacturing or production, and business owner.

Among them, construction is one of the identified drivers in the model. The other identified occupations do also correlate strongly with the groups identified by our Geo AI, e.g. installation or repair, farming, fishing/forestry, manufacturing/production are often self-employed, as business owners are as well. So we can see that some drivers from Geo AI align with empirical results from research studies.

Integrated in the platform TargomoLOOP, the Geo AI model delivers immediate prediction result for any potential address.

Insight #1 Good estimate of attraction strength is key 

Attraction strength indicates how attractive our stores are and how attractive/competitive our competitors are. A good estimate of attraction strength can better estimate the market size and potential customers, and thus predict the revenue more accurately. In estimating the attraction strength, information about the store is key, for example, store size, sales area, store opening hours. In this case study, due to the limitation of public data, the information we have is not enough to capture the whole picture of the store attractiveness, such as the missing information about the store size. To circumvent this limitation, the building roof top data is used instead, but it is not possible to obtain this information for all stores.

Insight #2 An attractive shop location is defined by its surrounding business environment AND access to its target group

When selecting a new location to open a store, investigating the surrounding businesses is critical. What products/services do they offer? What is their vibe? Are they competitive or complementary? However, the geographic distribution of target demographics can be missed in the decision-making process. It does not matter how well suited a location is to a store if the target customer group are unable or unwilling to travel to it.

Using Random Forest and XGBoost models, it is hard to control what variables are used in the decision tree. In this case study, these two models mostly focused on the nearby environment while giving only minor consideration to the access to target demographics. The Geo AI model both put a greater emphasis on demographics, and took into account a wider array of demographic and environmental factors. We have abundant data to measure various aspects of demographic structure to support the model and future decision making.

Insight #3 Expert knowledge could be a double-edged sword in key driver analysis. 

When selecting variables in the driver analysis, expert knowledge can provide insights on what key drivers can be expected based on experience or existing literature. At the same time, relying too much on expert knowledge and excluding data at the beginning that we thought is unrelated can fall into a bias trap.

Instead, by letting the model and data speak, we can gain new or unseen insights. We may find some variable we thought could be important have little to no significance, and vice versa. What we should then do is to investigate it, figure out why and explain it. Our assumptions should not interfere with the model.

The feature selection mechanism in Geo AI ensures the model suffers less from overfitting even with large number of features as the input.

This case study tests and compares the performance of three models, Random Forest, XGBoost, and Geo AI, as revenue prediction methods, using liquor sales data from Iowa, USA. Geo AI has the best performance among all 3 models in predicting liquor sales for Hy-Vee, having the least overfitting, the lowest testing error, and the important features in the model are more comprehensive.

Compared with Random Forest and XGBoost models, Geo AI takes greater consideration of shop feature factor variables, shop surrounding environment, local demographic structure, and mobility data making the model more reliable. In addition, Targomo’s Geo AI, a locational-based model, offers better understanding and evaluation of the characteristics of the shop location. It is possible to track the model and retrieve the prediction of each store to identify key revenue drivers. Due to its rate of overfitting and testing error, Geo AI could better predict the revenue of a new location and analyse revenue drivers.

Liquor sales prediction is one example of a Geo AI model. Geo AI can be applied in various industries, including among others retail, delivery services, food industry, and health care. Are you interested to learn more about Targomo’s Geo AI forecasting for retailers and restaurant brands, and see dynamic analytics of the Hy-Vee Geo AI model? Book a demo here

Authors: Yue Luo (Spatial Data Scientist), Gideon Cohen (Software Engineer), Luisa Sieveking (Marketing & Communications)

The Geo AI model was developed by Targomo’s Data Science Team that is dedicated to evaluate which location factors influence the business success of brands and companies, and to what extend they contribute to revenue.

The Innovation Insights Map project, which Targomo developed together with Germany’s largest housing provider Vonovia, has made it onto the shortlist for the Immobilienmanager Award 2023. The winners will be chosen on 9 March 2023.

With more than half a million flats in around 400 locations, Vonovia is the largest provider of residential real estate in Germany. One of the company’s declared aims is to actively shape neighbourhoods and offer tenants beneficial new services and innovative products.

But where is there a need for which service? Where should innovations be piloted? To answer these questions, Targomo has developed the ‘Innovation Insights Map’ in cooperation with Vonovia. The tool combines highly relevant data points to become the ‘single source of truth’ when the real estate company wants to locate and successfully implement new ideas or services for its tenants.

Data sets with over 500 data variables have been integrated and can be displayed on an interactive map as required. The three most important data categories are points of interest (POI) for around 350 categories, statistical data layers on socio-demographic characteristics and geo-referenced data on Vonovia’s buildings and existing services. This will not be the end of the story, however, as the platform has been designed in such a way that data from different sources can be added to at any time and users can even upload new location information themselves.

A thematic focus is on promoting environmentally friendly mobility and strengthening bicycle-friendliness in neighbourhoods. For this purpose, the Innovation Insights Map was supplemented with bicycle-related data and a Bike Attractivity Index (BAI) was developed. This follows a similar concept to the so-called “Copenhagenize Index”, but specifically assesses the accessibility of cycling-related facilities and the possibility to carry out everyday needs by bicycle.

A number of projects have already been successfully located and implemented thanks to the Innovation Insights Map, including an analysis of which areas are underserved with parcel stations and the use of mobile bicycle repair shops.

The Innovations Insights Map is nominated in the category “Management”. The award ceremony will take place on 9 March 2023 at the Motorwelt in Cologne and can be followed live on Immobilienmanager Magazin’s Twitter channel (@immomanager).

In previous articles we have already discussed what to consider when choosing a new location for a branch and which pitfalls to avoid. One key aspect in determining the success of a potential new shop is the environment. Do points of interest that attract visitors exist- if so, what kind of visitors? What other shops can be found here, are there competitors or complementary shops?

It’s no coincidence that retail activity is usually clustered in city centers and secondary shopping areas. On the one hand, locating close to competitors leads to the so called “competition effect”, meaning higher price competition and hence lower revenues. On the other hand, competitor and complementary shops nearby increases the overall attractiveness of the area and therefore capture more consumers. This is known as the “agglomeration effect”.  

The predominance of one effect over the other mostly depends on the type of business and especially on the possibility to differentiate the product that the business offers. For instance, gas stations offer a standard product where the price competition plays the most important role. Clothing shops offer instead a different range of products and can benefit from the presence of similar shops nearby. 

This is not surprising, those who want to buy clothes will find a wider choice in a shopping area with several clothing shops. The other shops act as traffic magnets, attracting more potential customers who might not have visited the store otherwise. This makes clothing brands the prime example of retailers that benefit from the proximity of competitors. They not only help increase footfall in the area, they even attract the right clientele who are looking to buy. 

This explains why the concept of “business clusters”, or more specifically, “shop clusters”, is extremely relevant in the retail sector. Shop clusters can be defined as a group of shops with similar or different characteristics that occur closely together.  We at Targomo use four attributes to distinguish between different types of clusters: 

The cluster size is determined by the number of shops that constitute the cluster. Usually, the more shops the cluster can offer, the more visitors it is expected to attract. 

How many different categories of shops constitute the cluster? How many different categories of shops make up the cluster? Is it a fashion strip, do furniture outlets congregate here? Or is the cluster perhaps defined by complementary shops such as a pharmacy, supermarket and drugstore? Industry clusters in particular can have a very positive effect on shops in the same category. 

What is the average price of the shops that form the cluster? As the saying goes, ‘Birds of a feather flock together’, and this can also apply to retail if they attract the same target groups. That’s why you usually see classy designer stores next to each other, but a jeweller only rarely next to a discounter. 

Do most well-known and popular brands compose the cluster, or independent shops and alternative designer labels? Here, too, like-minded shops often come together to define the character of a shopping street.

Investigating the impact of different types of clusters provides retailers with highly valuable insights into which characteristics drive their business success and what they should look for when selecting their next site. In fact, it is not only a matter of the quantity of footfall, but more importantly about the quality of the footfall around a store.   

To increase its profits, a business should locate itself in an area that attracts the right people. In other words, it should locate itself as close as possible to shops from which it could profit because they have the same target audience.  

At Targomo, our ‘success driver’ analysis looks at whether, and to what extent, being part of a particular shop cluster has a positive effect on sales. If we can determine correlations, retailers not only know which location attributes they should look for when opening a new site, we can also determine the “weight” (e.g. importance) of these attributes. The weighted attributes can be integrated into our sophisticated Geo AI model – a prediction model developed to forecast relevant sales metrics for any potential site.  

Our approach consists of three main steps: 

The Geo AI prediction model then defines exactly which characteristics lead a location to success and to what extent the respective location characteristics are contributing to success. To give an example: The results of a recent case study showed us that for a home furnishing retailer, price was the most important cluster characteristic. The brand particularly benefited from having many high-priced shops nearby. With this in mind, the brand has additional criteria when looking for a profitable area to open a new shop, specifically which are its best neighbors and hence the kind of stores that help making its business more successful.  

Author: Marta Fattorel is Spatial Data Scientist at Targomo. After graduating in Data Science at the University of Trento, she joined Targomo in Berlin to research the contribution of the various location factors to the turnover of the respective brands. 

While it might be tempting to just follow the gut instinct when it comes to planning a new retail store business, there’s a lot more that can be considered to guarantee success. From competitor analysis to catchment area data, leveraging everything at their disposal will help expansion managers make informed decisions and enable them to get under the skin of a neighbourhood to understand if it’s the right location or not. Here are the top tips for smarter retail expansion. 

When planning the next retail store business, it might be important to inject a local flavour. Creating exact duplicates of the original store is great for branding. But especially if it comes to international expansion, you might need to connect with local shoppers’ habits and cultures. It’s why McDonalds, for instance, caters its menu according to local tastes – fancy a slice of Malaysia’s Cookies & Cream Pie, or to chow down on Switzerland’s McRaclette Burger?  

The same logic might also explain why Starbucks, the biggest coffee chain in the world, failed to make an impact on the coffee-obsessed Australian market. Its blend was too sweet for cultured locals who were brought up on espresso from Italian and Greek immigrants and the company was forced to close 70% of its stores in 2018. Starbucks is slowly making a comeback in the country, aiming its wares at tourists, but it learnt the hard way that doing your research is key. 

It’s a fact of life that some locations do better than others, but when armed with the right insights, expansion managers can make a more informed choice from their desk, saving them the agony and expense of trial by error. If you’re a restaurant, for example, you’ll really want to drill into the foot traffic data: Is this area busy during the day and evening? Will there be lunch and dinner customers walking past? Are there good public transport options and car parking nearby?  

It is important to discover if a site is attractive by analysing how many potential customers can reach a location in a reasonable amount of time according to how they travel there.  Also the area’s key points of interest are essential and whether it, and they, are a good fit with the brand and product. The more data available, the better and sooner informed decisions can be made about whether the area is a good fit for the intended purpose.  

But finding the right data isn’t an easy feat either. Public data about the area may be unavailable, coming from untrusted sources, or fragmented by different sources (as an example, Germany has 16 official sources of public data). Although some businesses may need data scientists, you will want to choose a tool that can pull the data you need from trusted sources and integrate it with the data you already own. 

Once you’ve discovered everything there is to know about the area through location data, it’s equally important to get to know your potential customers. This means that you should learn more about the demographics of the area and see if this aligns with your target customer research. What did you learn about the audience of your existing shop that you can implement to improve the performance at the new location? Is your target audience likely to visit your new location? What competing businesses is your audience visiting in the area of your new shop? These, and more, are all the questions you need to answer before committing to a new location. 

But collecting data about the location and about your audience is not going to be enough to make an informed decision. You will have to clean, organise, prioritise, and analyse the data at hand. In other words, you will have to put the data to use. 

A tool such as the TargomoLOOP integrates numerous data variables such as demographics, purchasing power and foot traffic from trusted sources. Then sophisticated algorithms calculate what demand you can expect for a specific location and the entire branch network, and whether your stores may be cannibalise each other. You can even marry our location intelligence with your own business data to uncover correlations. You can try out different scenarios and instantly see which options are best for your next retail business. 

Interested to learn more about the analytics platform TarogmoLOOP? Request a demo and free trial. 

In a previous blog post we explored the potential of predictive analytics to help retailers plan future locations. Now, we lift the hood to find out more about how predictive analysis works and how it can benefit your business. Our guide is David Redlich, team lead for API Services & Data teams at Targomo.

Imagine if you could predict the performance of future new branches with a high degree of accuracy based on hard facts and not gut feeling. This is what we call predictive analytics. We combine machine learning and geo algorithms as well as socio-demographic, network and performance data to create unique predictive models that help our customers answer questions like: what makes my business successful? How many guests will come to my restaurant? How much revenue can I expect from my outlet store? Where should I expand to next? All of this analysis can now be answered within a fraction of the usual time and effort and with total control and transparency for you.

Typically, analytics has focused more on sub-aspects and couldn’t handle such large amounts of data. Take consultancies, for example. The analyses are static and usually limited to a few locations. This makes it impossible to run scenarios that take into account the interactions of different locations or look into the future. As the name suggests, predictive analytics are forward-looking. Once the model is in place, customers can perform in-depth analyses on any number of locations without noticeably changing costs. With TargomoLOOP, we have a really nice tool that allows our customers to do their own analysis and get powerful future insights based on data. The platform is scalable as this model can be used worldwide (depending on data availability). We’re confident we’re best in class at predicting a location’s future performance. Plus, we’re continually improving our models and tools.

In general, we use four sources: public, private, corporate and self-engineered data. 

Publicly-available data includes network data such as transit and traffic information, which we use to create mobility analysis patterns to see how people get to your potential new location. Also, socio-demographic and points-of-interest (POI) data are part of the public data.

Commercial data comprises additional fine-grained socio-demographic data, additional POI data, economic data like spending power or other relevant target group data such as Limbic Types. We obtain these from our reputable worldwide data partners.

An important part of the predictive model is, of course, our customers’ corporate data, meaning location-based data that provides insight into different store characteristics and performance. First and foremost are the sales figures. If we are to develop a predictive model for a specific KPI, we naturally need the data from the existing stores. Also, information such as different closing times, sales areas, etc are also important in order to examine their impact or to be able to explain deviations. 

Another relevant source that differentiates us from our competitors is successfully engineered domain-specific data. We provide foot traffic broken down by time of day and night, and on intentions such as shopping or restaurant visits. We offer car or home ownership ratios and custom POI sets that are particularly interesting brick-and-mortar businesses to see what complimentary businesses or services are around their sites.

At the beginning of a project, a considerable amount of time still goes into collecting, scraping and cleansing the data. This step is often underestimated but crucial in order to provide our customers with reliable results. The main challenge, however, is that AI and machine learning algorithms are usually not optimised for geo-spatial data (geo-information, POIs, network data and store locations). Getting those things to fit together is challenging. One of the things we did to solve that is the usage of established economical models – like the gravitational or logit models. In these models, all locations have an “attraction” with which you can calculate the probabilities of certain demographics coming to your place, taking into account other competing locations and their attraction. The complexity of the problem is incredible. Many people have tried to solve this problem with different levels of success. But, I believe, none have managed to in the generalised manner we have. Our predictive analytics works across domains. You can just plug in the data and find individual success drivers without any domain-specific or company-specific customisation. That is a pretty big challenge we overcame. 

One key influence for us is the user experience. For instance, we want to put TargomoLOOP entirely into the hands of our customers. We don’t want to act as the middleman doing the analysing for them. We want to give them a tool with which they can play through many different scenarios by themselves. It’s a fine balance – and we’re still learning how to communicate complex results but at the same time give our customers a lot of user control. We have always worked a lot with test users and collect feedback from existing customers in order to achieve a good user experience and to develop it further.

Customers play an important role before and during development. At the beginning, they provide us with the store and company data (e.g. KPIs) as well as environment-independent store facts. 

They then also have an active role during the evaluation. When we have the initial results on the success drivers, we run the results past them to see if it is comprehensible to them. It’s usually not a complete surprise what the success drivers are, but to what extent they are important. After all, we quantify exactly how important car and pedestrian traffic are on site and what role competitors play. After the analysis, they know how much of their sales are based on each factor. Sometimes we also find out that factors that were seen as important really have no impact on sales at all. 

It has been a steep learning curve for us and we created a research project together with universities to draw in knowledge that we didn’t have. We also expanded our teams with very capable data scientists. Together with our great software developers we created a successful symbiosis to offer cutting edge Geo AI as an enterprise product. I wouldn’t limit the needed skill set to that of data scientists or software developers, though. Marketing, business development and customer success are very important as well. It’s crucial the concepts and results are communicated in an understandable manner. That’s a difficult task.

David, thank you for taking us through predictive analysis. While none of us possess a crystal ball, as we’ve seen with predictive analysis, it really can help predict future outcomes in order to successfully plan retail locations and minimize risks. And the best bit is, the tool is intuitive to use, allowing our clients to plug-and-play to find the scenarios that work best for them.