Article appears in SAP Startup Focus Newsletter – Issue 1
An intriguing aspect of SAP HANA is the ‘Predictive Analysis Library’ or ‘PAL’. In SAP HANA SP05 ‘PAL’ is part of the broader ‘Application Function Libraries’ or ‘AFL’. The ‘Predictive Analysis Library’ contains a number of universal predictive algorithms that can execute directly against the data in HANA. PAL provides support for an array of Clustering, Classification, Association, and Time Series functions.
Many of the standard algorithms used in data mining and predictive analysis would be too onerous or even impossible to implement yourself in SQLScript; Yet if you want to perform real-time predictive analysis, you want to avoid exporting your data to an external application server to run some predictive analysis function. The answer in SAP HANA is PAL. The idea behind PAL is to make it very straightforward to execute, for example, a clustering calculation like K-means on your data in HANA with a few lines of SQLScript. In most cases you need to identify your Input Table, populate a Parameter Table (setting up the parameters of the function), and identify an Output Table, and let HANA and PAL do the rest.
If you would like to learn more about PAL, check out the HANA Guide for PAL at http://help.sap.com/hana/hana_dev_pal_en.pdf. Also check out the SAP HANA Academy (http://www.saphana.com/community/resources/hana-academy).
David Sonnenschein is part of the SAP Startup Focus Program’s Development Accelerator, helping early stage companies adopt the SAP HANA Platform across a broad spectrum of domains.
VN:F [1.9.22_1171]HANA Curious? - Predictive Analytics Library,