Online content and service providers like Netflix and Amazon have popularized the use of recommendation platforms/engines, that predict a user’s preferences based on historical ratings, collective user profiles and behavior. Collaborative filtering is the collective term for machine learning algorithms used by these engines to make personalized recommendations from extremely large datasets. Performance, accuracy and scalability are critical factors that determine the suitability of these systems in real time environments. This webinar highlights the significant performance speed-ups achieved by implementing multiple Intel tools and techniques for high performance Python on collaborative filtering methods benchmarked on the latest Intel® platforms. A combination of performance profiling with Intel® VTune™ Amplifier XE, accelerated machine learning algorithms in Intel® Data Analytics Acceleration Library and Intel® Distribution for Python*, and enhanced thread scheduling, showcase the individual strengths and combined computation power to drive performance on large scale machine learning workloads
Download Slides PDF [4.72 MB]
Benchmark results were obtained prior to the implementation of recent software patches and firmware updates intended to address exploits referred to as "Spectre" and "Meltdown". Implementation of these updates may make these results inapplicable to your device or system.
Software and workloads used in performance tests may have been optimized for performance only on Intel® microprocessors. Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more information, see Performance Benchmark Test Disclosure.