How to integrate KXEN result with own apps?

[richard_gu]

Dear Experts,

When I was trying the Association Rule of KXEN (SAP infinityinsight 7.0), I do not find a good way to integrate the trained result rules into my own App. When I got a group of rules, the only way I could think is to save the rule list into the html file and then manually (or write a program) to convert the rules in html file into my database tables;

Is there any better way that I could save the rules directly into my table? or even to generate SQL (like in classification) would be  much better?

Thanks

[Former Member · Accepted solution]

Hi Richard,

As you noticed, implementing rules produced from SAP InfiniteInsight Modeler - Association Rules is not simple.

This component is deprecated and has been replaced by another one which is much easier to use and implement.

I suggest you use SAP InfiniteInsight Recommendation (should be accessible on your current instance of SAP InfiniteInsight).

You'll be able to generate source code (SQL codes optimized for many different databases) and will be able to specify how many recommendations to push to each customer, whether or not best sellers must be included in recommendations and if it makes sense to recommend again a product that was already purchased by a customer. 
Besides, Recommendation is using a different technique than traditional Association rules (which use A priori algorithm) and it scales on huge volumes of data.

On the licensing side, SAP InfiniteInsight Recommendation is an add-on that can be purchased on top of  InfiniteInsight Engine.

Armelle

[richard_gu · Accepted solution]

Dear Armelle,

Thanks for the reply.  I checked the new "Recommendation" and found it looks to be very similar to the Social Network Analysis (Transactions). So to my understanding, this recommendation function is different to the Apriori algorithm and they are addressing to different scenario:

Apriori: for a transaction , when you choose one item, using the rules to tell him what else he could buy

Recommendation:  for an existing customer, what else he could buy? it is not used on an happening transaction, but used in the case like periodic recommendation.

So I think they are not 100% equality... How do you think?

[richard_gu · Accepted solution]

BTW, could Social Network Analysis generate SQLs (I didn't find)? for example, I have original links data set in a table and want to us a SQL generated by KXEN to get another table which contains the predicted (virtual) links between the nodes?

I guess  it may be very hard using SQL to describe the algorithm.

Thanks!

[Former Member · Accepted solution]

HI Richard,

You're right on the similarities between Social and Recommendation.

Actually, Recommendation is a subset of Social (transactions and their derived graphs). This interface has been simplified to make it more usable and business-oriented.

Both tools will provide you with recommendations for returning customers (or identified customers).

Association Rules will provide you with a recommendation once the new customer has selected a first product.

Recommendation can provide suggestions even if the new customer hasn't selected anything (in that case, we will push "best sellers", provided the option has been selected).

To my mind, there are differences between the 2 tools but both are providing rules that can be applied to existing and new customers.

Armelle

[Former Member · Accepted solution]

You're right, Social is not exporting code (SQL or others).

Social is not part of "InfiniteInsight Modeler" as it is not a predictive tool, this is a descriptive tool. It enables to create the network of individuals and compute their social attributes.

It cannot "predict" for a new user, what his connections or social attributes will look like.

Maybe you can email me with more details on what you would like to do and we'll try to figure out how to do it.

Armelle