From June 2016 to February 2018, we conducted the Customer Prediction Platform (CPP) research project. This strategically important project was co-financed by the European Regional Development Fund (ERDF) and the Investitionsbank Berlin Brandenburg (IBB). Now that the reporting and evaluation phase has been completed, we would like to present some highlights of this project below.
CPP is a middleware for assessing the customer potential of corporate customers. The paradigm shift of CPP is that public contextual knowledge about companies is incorporated into a fully automated recommendation for end users in B2B marketing. In the case of inbound leads, for example, individual product recommendations can be calculated.
Concrete subgoals over the entire period consisted of:
Increased transparency in customer recommendations
Automatic categorization of new companies into user-defined categories
Setting up a comprehensive event monitoring system
Analyses of company websites and recorded news
Three results of the research project that we consider to be particularly important:
First, we launched the open source project DALPHI Active Learning Platform for Human Interaction to implement the continuous iterative process of improving machine learning models. This iterative improvement is achieved with the help of the Active Learning technique. From unannotated data, the model independently identifies those for which knowledge of the correct output would offer the greatest added value. These are typically those examples that are “close to the decision limit”. These examples are then presented to a human annotator. Then these now annotated examples are added to the training data set and a new model is learned with this now larger training data set. The current version of the software includes the administration of different annotation interfaces, which can be adapted to different questions.
Next, we would like to highlight the CATEGORIZE function developed in the project. This feature will particularly enrich our service Implisense. It allows you to score any company for affinity to custom profiles. This means that a lead can no longer be qualified just according to traditional criteria such as region, industry or size, but according to one’s own profiles, such as the profile of the customers of a specific product. From a technological point of view, we have succeeded in “reversing” our well-known recommendation function and finding the right profile for the individual company.
Finally, we would like to draw attention to the comprehensive event monitoring, which was also developed within the scope of this project. In addition to announcements in the commercial register, we now provide you with news, job advertisements as well as blog and social media texts. We do not only record articles from a high five-digit number of sources, but we also process each recorded article and assign it to the correct companies. Technologically, questions of Named Entity Recognition (NER), Named Entity Disambiguation and relation extraction were addressed here. In the future we will also present further approaches for automatic tagging and prioritizing. Many of our customers are already benefiting from this development in products such as our Software-as-a-Service solution Implisense Pro or our Implisense API.
This article shows how you can create a list of companies that use a certain technology with just a few clicks and with the help of our partly free tools.
This list then can be conveniently used within our web application or offline as an Excel table in sales or marketing.
As an example we are searching for the use of MailChimp. The technologies that can be searched for in this way also include CRM systems and marketing or social media tools such as Google Adwords, Google Analytics, Zapier, Salesforce, Twitter, Facebook and others.
Reading time: 3 min
For use in: sales and marketing
Don’t want to wait?
We are often asked by our customers to identify companies that use certain technologies and provide them as a list with contact information and addresses. Implisense has a number of methods to determine the techstack of companies from freely available online sources, e.g. by text mining on job ads of companies or by evaluating the technical information in the code of the company websites. Usually you can request company lists from in-depth analyses directly from our team of analysts. However, certain software can be found directly through our search function. So if you don’t want to wait, here are instructions on how to create and view your own company list.
Example: Target group mailchimp users
As an example we take the use of mailchimp. Mailchimp is a cloud-based solution to automate your email marketing. This technology is therefore an indicator of a company’s focus on online marketing and newsletter distribution, for example. This software is often used by young, dynamic or at least digitally affine companies and employees. It enables the addressing of a broad audience with relatively little effort, is therefore also suitable for the marketing of scalable products and allows the integration of various additional plug-ins for the analysis and automation of product marketing.
Whether you offer an alternative solution to this software, or you are only interested in companies that tend to be willing to try out new technologies and/or practice online marketing, you may be interested in this target group.
1. Search in the Implisense company index
The feature we would like to introduce to you in this article is the search for certain company attributes via dedicated company websites.
Of course, not all technologies used by a company are covered on the relevant pages. However, these are often mentioned on career pages, are subject to a disclosure obligation by legal standards, are visible as plug-ins on company websites or are mentioned in the declaration of processes and services.
In this sense, data protection declarations in accordance with the General Data Protection Regulation (GDPR) provide an interesting insight into the technologies used. Companies that integrate third-party providers into their data processing processes are instructed to list them accordingly in their data protection declaration. These are often cloud-based solutions, from CRM systems and marketing tools to social media and rating agencies. This includes not only MailChimp, but also Google Adwords, Google Analytics, Zapier, Salesforce, Twitter, Facebook and many more.
2. Find prospects for free
To get an initial overview, you can search over 500,000 German company websites free of charge on our Companies and Markets search platform directly after naming these technologies and see the first hits. The simple search for “MailChimp” entries shows that not all companies that mention this software on their website are necessarily users of this software. These include providers of IT services or software manufacturers whose products can be linked with MailChimp.
We have thus found a reliable indicator for our target group.
If you now search for the link “mailchimp.com∕legal∕privacy”, for example, you will get the desired result. The hit overview already shows that the top hits found use Mailchimp as a newsletter provider.
This can be traced for each of the hits by calling up the company profiles. Here you will not only see all the entries of your search criteria on the company website. In addition, depending on the coverage, we offer you information such as the company purpose, the company headquarters, and selected past events that we have recognized about this company.
Lead generation, segmentation and qualification with Implisense Pro and free companies-and-markets alerts
If the search options are not enough for you or you don’t want to wait, you can test our web application Implisense Pro free of charge for full lead generation in B2B. In addition to the search, various filter criteria and our scoring function for the automatic determination of potential customers are available here.
However, if you are interested in certain company events, then register for the free test phase of our company alert. This allows you to receive a notification stating technologies, trends, etc. as soon as our systems recognize companies that are named together with these terms and topics.
Up to 18,370 companies could be affected by a renewed deterioration in political relations between the West and Iran.
Since 8 May 2018, it has become clear that the political conflict between the USA and Iran could also endanger German companies’ trade relations with Iran. A current analysis of data on the larger 600,000 companies in Germany shows that up to 18,370 companies have publicly named economic ties to Iran. The spectrum ranges from suppliers with sales offices, buyers of Iranian products to forwarders who can transport goods to Iran.
Medium-sized companies could be disproportionately affected by economic sanctions. With 2,039 hits and 14.14 percent in the sample, their share of potentially endangered companies is about twice as high as in the population analysed. But large companies have also established economic relations with Iran, with 579 large companies in Germany using this methodology.
In addition to certain sectors, specific regions could also be particularly affected. The nationwide distribution of Iran-related companies suggests that urban centres in particular could be severely affected by a negative development in relations with Iran. Accordingly, the density of relevant companies is highest in the large cities of Berlin, Hamburg and Munich as well as the Ruhr area. The regions outside the big cities are also interesting. Nuremberg, Bielefeld and Hanover stand out here. Moreover, the financial stronghold Frankfurt seems unexpectedly to be the location for more potential affected companies than Stuttgart, a focus region of export-oriented automobile manufacturers and machine builders.
Would you like to find out for yourself which companies from your region or industry could possibly suffer from an escalation of this international conflict? With Companies and Markets you can easily research which of these companies have a reference to Iran on the website or in the company name. Do you have any questions about the analysis? The easiest way to contact us is at firstname.lastname@example.org
Based on a current data collection from our company index on April 30, 2018, only 10,775 companies from Germany have modified their data protection declaration in response to the new General Data Protection Regulation (GDPR). The evaluation indicates that micro-enterprises in particular are struggling to implement the more extensive requirements. Companies with business models in which data and data exchange play a critical role take advantage of the opportunity to proactively adapt their data protection.
About Implisense: The Berlin-based start-up Implisense is one of Germany’s leading providers in the field of B2B lead generation. Our text mining procedures analyze online content for all companies listed in the commercial register and located in Germany. The data obtained are assigned to the companies as structured characteristics and thus enable to identify, evaluate and observe potential business partners, customers or competitors from a new perspective.
The General Data Protection Regulation is approaching and putting pressure on many companies. Serious penalties linked to company turnover are imminent. At the same time, the new requirements, for example in the areas of documentation, data security and transparency, should not be underestimated. It is not uncommon for managing directors, authorised signatories or data protection officers to sit in front of never-ending checklists, create biblically-sized documentations, and finally make a revised data protection declaration of often far more than 10 pages available.
After all, the fair use of personal data by the private sector is an issue that society and legislation must constantly keep up with in times of drastically developing information technologies.
Against this background, Implisense has investigated how many companies are highly likely to have already addressed this issue and updated their data protection agreements. For this purpose, we have calculated the distribution of relevant signal words – such as the direct reference to the now applicable European Directive, synonyms (e.g. GDPR, General Data Protection Regulation and the German term DSGVO), and typical formulations – on company websites. The occurrence of the indications was then faceted with a view to other company characteristics, such as industry affiliation and size, in order to identify the associated characteristics.
Only one of 50 companies has adapted the data protection declaration
Even if the possible additional costs of implementing the new regulation are taken into account, the result is surprisingly clear. Our analysis suggests that only 10,775 companies have references to an adapted data protection declaration. This is all the more remarkable with a total of approximately 593,337 active companies registered in the commercial register and with sufficient data. This corresponds to approx. 1.8% or 1 of 50 companies.
A potential aspect can already be anticipated when looking at the distribution of these companies over the size of the company. Smaller companies in particular are struggling with the new requirements. For example, we estimate that micro-enterprises account for around 69% of the total. For companies with GDPR references, this shrinks to 61%. Large enterprises, on the other hand, are almost twice as often represented as in the total volume at 3%. The following graph compares the size distribution of companies in the population (left) with the estimated distribution of companies with updated data protection declaration (right).
The potential link between company size and data protection update suggests that certain industries and business models could also be more strongly associated with it. The graph below shows industries that are disproportionately frequently represented in the hits (top 20 in order; WZ 2008) and their absolute number of hits.
The IT sector, for example, is most over-represented (J62). With 2,732 hits, these also account for the bulk of companies with an updated data protection declaration. Other sectors with data- and communication-intensive business models dominate the list, e.g. IT service providers (J63), the retail sector (G46, G47), lawyers (M69), financial service providers (K64) and consulting firms (M70). So if companies have updated their data protection, it is probably only because an extreme amount of data is generated on the basis of their business model. Slightly unexpectedly, the crafts (F43), electrical engineering (C26) and metal production (C25), as well as the education sector (P85) are to be found in it.
Exemplary hits on companies with updated data protection declaration from a greatly simplified analysis can be viewed directly on our platform Companies and Markets:
Our small analysis to identify companies that have already dealt with the GDPR is based on probabilistic methods and is therefore not necessarily representative. It covers companies that are only highly likely to have already done their homework on the General Data Protection Regulation.
It can also be further refined. As the example of training providers in the field of GDPR shows, e.g. by excluding certain sectors from the analysis. Finally, it does not necessarily state that existing data protection policies at companies that were not in the hit list are not already professionally designed and may only need to be formally adapted. In our opinion, the effects of these restrictions cannot call into question the basic findings of the evaluation.
Only a fraction of companies in Germany are finally prepared for the General Data Protection Regulation a few weeks before the implementation deadline expires. There is evidence that micro-enterprises in particular find it more difficult to ensure implementation. If so, then companies with particularly data-intensive and communication-intensive business models tend to implement the new data protection regulations. The question is, what business models in the age of digitization can still afford not to work with data to an appropriate extent?
In this blog series we would like to present some insights from our Scoring projects. Specifically how Implisense Data Scientists determine target customer profiles for selected products and services of key customers. The following insights were gained from Implisense’s data without the need for costly internal data processing at the customer’s premises. The preconditions for analysing the target customer profile are low. Our clients typically name 10-30 company names of sample customers in an Excel file, so that our Data Scientists can calculate a target customer profile on Implisense’s company data. For reasons of confidentiality, the names of the sample customers are not mentioned in the blog posts, but only the analytical results are presented and interpreted for you.
High-quality video conferencing solutions
A vendor of high-quality video conferencing solutions with regional marketing units want a more precise targeting of German companies and a better value-added communication especially for German medium-sized businesses.
The vendor sends Implisense a number of exemplary customers of its video conferencing solution in Germany. The Implisense Data Scientists first perform an automated matching of the company names with the database of Implisense. Then they use the matches for the Big Data Analysis. The Data Scientists use all information available in the Implisense system about the mentioned companies and all other 2.2 million companies in Germany.
Generated Target Customer Profile
The target customer profile for customers of high-quality video conferencing solutions is geographically focused in the postcode areas 71 – Stuttgarter Umland, 70 – Stuttgart and 68 – Mannheim. Existing customers typically employ employees in classes 501-1000, >1000 employees and 101-500; there is no evidence of smaller companies. All customers report annual sales of >100 million euros. The primary industries for users of high-quality video conferencing solutions are C: Manufacturing, followed by G: Retail; Maintenance and repair of motor vehicles and G46: Wholesale. Thematically, existing customers emphasize the quality of their products and services in their external communications with 56%, innovation with 53% and intelligence with 50%. The companies have an above-average number of locations in the following countries, sorted by decreasing importance: China, Japan, Brazil, Malaysia, Thailand, Singapore. Furthermore, the companies emphasize their substantial research activities with their own organizational units and their technologically sound product portfolio. The companies report strong growth over the last few years.
Interpretation of the Target Customer Profile
A sales story can be derived from the determined target customer profile. Accordingly, target customers of high-quality video conferencing solutions are likely to have a need to protect their technological know-how in view of the high communication efforts required by their international locations. Therefore, marketing should appeal to companies that have these structural characteristics and establish or expand locations in China, Japan and Brazil. Potential users should be found in the sales department, with emphasis on simplicity and reliability of the solution. Addressing users from research and development should also be examined, with an emphasis on knowledge protection through secure international communication and cooperation. In view of the margin situation for technologically leading and fast-growing companies, the costs and prices of the solution should play a rather minor role. Due to the technological affinity of the target customers, live demos could be more convincing. Furthermore, recommendation marketing should be used, as many of the sample customers are connected with potential new customers directly or through industry associations. This fact should be used in marketing and sales via personalized success cases with the naming of the linked business partners.
Recommendations of potential customers
The best match of the Implisense Lead Recommendation is Infineon Technologies AG. This company has substantial technological know-how, operates internationally in China, Japan, Brazil, Singapore and is connected to numerous reference customers.
In addition to Infineon Technologies AG, more than 1,200 other companies can be identified in Implisense Pro alone, which match the determined target customer profile and can be approached via the regional sales structure. Through the Implisense API, the client’s CRM team can create regular queries about which potential clients are notified of changes in the international locations and then implement automated 1:1 marketing campaigns for high-quality video conferencing solutions between the client’s headquarters and its international location.
Summary / TL;DR
Using exemplary buyers of a high-quality video conferencing system, Implisense data can be used to calculate meaningful target customer profiles within a short period of time. The target customer profile points to internationally active companies from Germany with technological know-how worthy of protection and sales and research units in Asia. These results can be used to address existing and potential customers 1:1 and can be integrated into automated marketing processes.