_{[News Viscovery]}

Linz (AT), 17 October 2024

Data mining specialist Viscovery has released the latest version of its Viscovery® SOMine® software suite designed to help customers uncover high-value insights from complex data sets and make accurate and comprehensible predictions.

Viscovery SOMine 8.1 provides several new features and usability improvements aimed to further streamline data pre-processing, model building and evaluation. Researchers will especially benefit from the automatic calculation of adjusted p-values for statistical tests and quality measures for classifications on both the macro level of classes and the micro level of records. For business users with large amounts of data, the main benefits are likely to be the more flexible import capabilities, computations running in the background and improved presentation for quick reports.

For a complete list of notable changes, see: What's new in Viscovery SOMine 8.1

Viscovery SOMine version 8.1 consists of several flexibly combinable modules focused on specific analytics applications. Each modular configuration is available as a perpetual license and as a term-license for the period of one year. In addition to single-user licenses, network licenses are also available allowing the software to be used by multiple concurrent users on a local network.

Visit https://viscovery.net/visual-explorer to download the basic module Visual Explorer and test it for three full months free of charge or any other obligations. The trial period ends automatically, without any need for interaction.

To get access to the full capabilities of our dedicated extension modules Cluster and Classify, Predict and Score, Enterprise Data and Workflow Automation visit viscovery.net/somine or contact sales@viscovery.net.

_{[News Viscovery]}

Linz (AT), 19 August 2024

We are proud to announce Viscovery's 30th anniversary. We are pleased that we have been able to build many great customer relationships over this long period of time, and to continuously improve our software thanks to the expertise of our employees and always with an eye on the needs of our international customers from all areas.

We hereby cordially invite you to celebrate with us. You have given us your trust or are giving it to us now, and we are giving you a 15% discount on all licenses ordered until the end of our anniversary year 2024.

Get your license now and be amazed at the possibilities and insights you gain with Viscovery:

Anniversary single-user annual licenses are available in the webshop (https://www.viscovery.net/somine/) with the discount code "30years". For perpetual licenses or network licenses, please contact us by email (https://www.viscovery.net/contact).

We also invite you to connect with Viscovery on LinkedIn to stay up to date with news.

Viscovery‘s History:

Viscovery was founded by Gerhard Kranner in 1994 under the name Eudaptics Software GmbH, which was renamed to Viscovery Software GmbH in 2007. Gerhard Kranner led Viscovery as its managing director for over 27 years. In this time the Viscovery products were introduced which were the first commercial software packages world-wide for self-organizing map applications. Over the years the Viscovery products were refined and expanded with new state-of-the-art algorithms and Viscoverys own inventions, like the local SOM prediction (2002), the Viscovery Big Data visualization (2017) or the Connectivity clustering (2022).

In 2008, Viscovery was listed as the only data mining vendor in continental Europe in Gartner’s “Magic Quadrant 2008 for Customer Data-Mining Applications”. For many years now, Viscovery software is being used by numerous customers from different application areas, such as life sciences, manufacturing, banking, insurance, telecom, media, retail, as well as research organizations and universities on all continents. This led to over 500 scientific articles using Viscovery technology, see https://www.viscovery.net/scientific-articles for a curated selection of them.

In 2022, Gerhard Kranner handed over the day-to-day business to the younger generation and guided Viscovery into the Viscovery AI Alliance, a new project of Viscovery Software GmbH with its owners Microstep AG and STAT-UP GmbH, to provide an even better and more comprehensive product and service portfolio to its customers. Apart from Viscoverys high performance software and its specialized training and consulting services, the Viscovery AI alliance offers a wider range of data science and statistical consulting, contract research and interactive and cloud-based software services around data and its applications.

The Viscovery team invites you to join us into the future. Connect with us through LinkedIn or on upcoming events and get to know our current projects and technological advances.
 

_{[News Viscovery]}

Duisburg (DE) / Munich (DE) / Linz (AT), 27 August 2024

In September and October, Viscovery offers a free webinar (in german language) in which we discuss the uses of self-organizing maps for target group analysis in fundraising of NPOs.

In cooperation with Cloud und Rüben gGmbh – an expert in the field of digitalization for the non-profit world – we discuss the possibilities of optimizing fundraising efforts on real and anonymized donation data of an NPO.

See Webinar KI-Analyse des Spendenverhaltens for our corresponding linked-in article.

For charitable organisations that rely on donations, it is essential to use their funds efficiently and target donors. Understanding donor behaviour plays a key role in this - from the amount and frequency of donations to preferred donation purposes and payment methods. In this article, we take a look at how to analyse these aspects using Self-Organising Maps (SOMs) to gain valuable insights for your fundraising strategy.

With the help of Viscovery SOMine, we analysed the donation behaviour of 5199 donors of a non-profit organisation (NPO). The self-organising map helps to display complex data in a two-dimensional map and to identify homogeneous clusters.

For our analysis, we took various factors into account, including the average amount of a donation, the number of donations per year, the total amount donated per year, the month of donation, the proportion of free donations, the payment method and the purpose of the donation. We also differentiated between private individuals and organisations. For data protection reasons, we did not have any further information on the donors, such as gender, age or profession. Nevertheless, the analysis provides revealing information about donation behaviour.

The resulting model shows 9 clusters:

Figure 1: Cluster der verschiedenen Spender

As can be surmised, the average donation amount varies from cluster to cluster. There is also a clear variance within the clusters. Organisations in particular often make higher donations. The following illustration shows the average donation amount in the individual areas of the donor map.

Up to 70 very similar donors are assigned to each hexagon in this map - an average of 5.3 donors per hexagon.

The average donation amount is represented by the colour of the hexagons, with dark blue corresponding to €0, light blue to €30, turquoise to €70, green to €250, yellow to €1000, orange to €3000 and red to a donation of €5000. A logarithmic scale (with offset = 10) was chosen in order to be able to resolve the different areas well):

Figure 2: Mittlere Spendenhöhe, logarithmische Skala (Offset = 10)

What is also interesting in this context, however, is the donation frequency, which is higher for private individuals, especially for frequent donors, but also for direct debit donors and mixed donors.

In the following illustration, the colour coding is given by the donations/year, where dark blue means 0.5, light blue 1, turquoise 2, green 3, yellow 6, orange 8 and red 12. Once again, a logarithmic scale (offset = 1) was chosen for the visualisation.

Figure 3: Mittlere Anzahl der Spenden pro Jahr, logarithmische Skala (Offset = 1)

This results in the following more balanced picture for the donation volume calculated over one year. This is again a logarithmic scale from 0 to 5000 with offset = 10.

Figure 4: Mittlerer Spendenbetrag pro Jahr, logarithmische Skala von 0 bis 5000 (Offset = 10)

In this context, we are particularly interested in frequent donors, as they generate an ongoing cash flow that adds up to considerable sums over the year. Many of these donors also pay by direct debit, which is a sign of a closer bond between the donors and the NPO.

The following chart shows which projects the frequent donors have donated to most frequently. The percentage of donors in this cluster for the respective donation purpose is shown:

Figure 5: Auflistung der Projekte nach Häufigkeit der Spende

Finally, we are interested in which fundraising campaigns the frequent donors responded to with an above-average number of donations. For this purpose, a profile value (Hedges g*) is calculated, which relates the difference between the cluster and the population to the average statistical fluctuation. Only those differences are shown that are statistically significant (significance level 95% taking into account a Benjamini-Hochberg multiple testing correction).

Figure 6: Auflistung der einzelnen Fundraising-Aktionen nach Erfolg

It can be seen that Aktion-PP-nn is very strongly overrepresented. In fact, 71.9% of frequent donors were (also) approached through this campaign. Across the entire data set, this applies to only 2.7% of donors. Just like the second-ranked campaign-MF-nn, the campaign-PP-nn is a permanent campaign that extends over the entire observation period. Unfortunately, we do not have any more detailed information on the individual campaigns. The time-limited campaigns N21, N13 and N15 are also overrepresented in this cluster. Action-HS-nn and Action-KK02 are the most underrepresented FR actions. It can therefore be seen that varying target groups (here, for example, the frequent donors) are also addressed very differently by different campaigns.

Our model can help to analyse the fundraising campaigns with regard to previous donors and to define hypotheses as to which types of campaigns can lead to success with which contact person. Quantitative testing of these hypotheses is not possible with the model, as negative results (people who were contacted by the campaign but did not donate) are missing from the data. Such data would have to be collected when implementing future FR campaigns. Personal or company-related data on the individual donors would also be of great benefit for optimising target group selection.