Angoss touts flexibility, ease of use

Toronto-based Angoss Software Corp. says there’s a pile of data in most organizations that’s just waiting to be mined, and the latest version of its flagship data mining tool can help make the task a relatively easy one.

The tool is KnowledgeStudio Version 2.0., a generic data mining workbench or framework designed to work with all forms of data, no matter what industry the user does business in, said Ken Ono, vice-president of technology at Angoss.

“(KnowledgeStudio 2.0) can be used with any data in any industry. The data mining component can be embedded as part of an overall solution, or tailored to a particular vertical industry application,” Ono explained.

This is made possible because of KnowledgeStudio’s integrated ActiveX technology – for predictive modelling – and DCOM architecture, he added.

Ono said the whole notion of data mining is moving away from the exclusive domain of statisticians and database administrators, and into the hands of the everyday business user. That’s why KnowledgeStudio 2.0 ships with an object-oriented Microsoft Office user interface, which is also integrated with Microsoft’s SQL Server 7.

Version 2.0 comes with five decision tree algorithms, three neural net algorithms and one so-called “unsupervised” learning and clustering algorithm. Third parties can add on algorithms where they see fit, Ono said.

KnowledgeStudio integrates with data warehouses and data marts, so that it is possible to mine data “in-place” via query waves. Also, data can be extracted and mined in KnowledgeStudio’s own data server.

Ono said KnowledgeStudio functions on networks as well as on workstations or servers. And data exploration, whether through decision trees or graphics, can be deployed via an Intranet. Java-based model deployment and data exploration is soon to be added, according to Angoss.

And, Ono noted, KnowledgeStudio 2.0 is very scalable. “One of our big customers is a company that makes supercomputers out of England,” he said. “And they’ve [integrated] our technology, so in conjunction with that computing power…it’s possible to mine hundreds of millions of rows.”

Paul Tyndall, manager of predictive modelling for the Royal Bank Financial Group’s (RBFG) Wealth Management division in Toronto, said KnowledgeStudio is a valued addition to his business intelligence application suite. Tyndall provides RBFG’s various divisions with predictive modelling based on client information, in a SAS-based business intelligence environment.

“We found that it fits the niche that we were looking for, filling in the gaps we couldn’t fill using SAS on its own,” he said, adding that SAS provides some but not all of his data mining needs.

Of all the functions, he said there’s one that has impressed him more than others. “It’s really tree functionality that’s the number one go-to functionality for us. It’s really the kind of functionality you can’t replace by other means.

“And in terms of the interface, I’ve found that it’s far superior to the other versions of it out there in the market, and at a good price point.”

Tyndall said limitations are not an issue, since KnowledgeStudio is a framework. “It’s a fairly open architecture in that new things can be added relatively easily to it…so one of the things that you hear about in data mining is to try a lot of things, and whatever works bests, that’s your answer.”

The KnowledgeStudio 2.0 (www.angoss.com/products) client or stand-alone workstation runs on Windows 9x or NT. The data mining component, KnowledgeServer, runs on Windows NT Server and NT Workstation. A Solaris version will be available soon.

Database formats supported include Access, dBase II, III and IV, ODBC, SAS, and SPSS. Data mining algorithms supported include CHAID, XAID, K-Means and Entropy decision tree algorithms, as well as multi-layered perception, radial basis formation and probabilistic neural nets. Under development are Kohonen, C4.5 and regression algorithms.

Also available from Angoss in beta format are KnowledgeExcelerator and KnowledgeAccess, designed specifically to mine data from Microsoft Excel and Microsoft Access respectively.

The price of a single, stand-alone workstation KnowledgeStudio 2.0 (www.angoss.com) seat is $6,000.

Angoss Software Corp. in Toronto is at (416) 593-1122.

Would you recommend this article?

Share

Thanks for taking the time to let us know what you think of this article!
We'd love to hear your opinion about this or any other story you read in our publication.


Jim Love, Chief Content Officer, IT World Canada

Featured Download

Previous article
Next article

Featured Articles

Cybersecurity in 2024: Priorities and challenges for Canadian organizations 

By Derek Manky As predictions for 2024 point to the continued expansion...

Survey shows generative AI is a top priority for Canadian corporate leaders.

Leaders are devoting significant budget to generative AI for 2024 Canadian corporate...

Related Tech News

Tech Jobs

Our experienced team of journalists and bloggers bring you engaging in-depth interviews, videos and content targeted to IT professionals and line-of-business executives.

Tech Companies Hiring Right Now