Predictive Modelling and Advanced Analytics using R
This course is an introduction to a range of fundamental skills, techniques and tools for those aspiring to become Data Scientists. These include Big Data, Machine Learning and Cloud Computing. Data Science, Predictive Modelling and Big Data skills are of vital and growing importance in commercial, government, commercial and not-for-profit organisations.
Those in the Management, Product, Risk and IT functions benefit from skills and literacy in this area. This two-day course introduces a range of techniques as they are commonly used in business, and provides practical experience in their use.
Attendees should, by the end of the course:
- Learn fundamentals of predictive modelling and experience using a range of methods.
- Have improved their ability to assess the effectiveness and fitness for purpose of any predictive modelling tool or technique.
- Have expeirence with a range of unsupervised data techniques. Be exposed to Big Data and Cloud Computing applications.
This course is suitable for anyone in management, administrative, product, marketing, finance, risk and IT roles who work with data and want to become acquainted with modern data analysis tools.
Attendees are recommended to have completed Presciient's 'Introduction to R' two-day course, or equivalent. This is a helpful but non-essential prerequisite.
The course will be led by Presciient Director, Dr Eugene Dubossarsky. He is the head of the Sydney Users of R Forum. Eugene is also Principal Founder of Analyst First, an international analytics industry organisation. He is a founder of the Institute of Analytics Professionals of Australia (IAPA); Director, University of New South Wales School of Mathematics and Statistics Industry Advisory Board; and a recognised industry leader in Business Analytics.
Eugene is an experienced, analytics professional of 20 years' experience programming in R and its parent language, S.
Although these courses are confirmed to run, Contexti & Dr Dubossarsky reserves the right to cancel any course due to insufficient bookings and will notify and refund attendees in such cases.
"Thank you very much for the information I gathered at the Predictive Modeling course I attended recently. As a beginner in R, I thought that it might be a bit overwhelming. But I was wrong! Eugene did a fantastic job at explaining the concepts and all practical work was engaging and easy to follow. Entertaining, informative and most importantly relevant - it has already proven valuable in my work."
- Sanja Djekic - Data Manager/Analyst at South Western Sydney Local Health District
"I attended the Predictive Analytics course presented by Eugene Dubossarsky from presciient.com in March of 2013 in North Sydney. I am primarily a computer scientist, and have a broad but very shallow knowledge of the area of machine learning and analytics. The course gave me a very good starting point to start gaining a deep knowledge of the topic. The tooling presented gives an excellent place to start learning and is useful beyond the class setting. I think the key value of the course is that it was presented by a domain expert who is passionate about the topic and growing the maturity of the field; and so was very open with the sorts of insights that you don't read in a text book. This included the high level concepts within analytics, models of thinking about analytic problems and key lessons from his career implementing predictive analytics. I therefore left the course knowing what I don't know, and knowing where to start, which is more than I expected. I would recommend it to any computer scientist."
- Quinton Anderson - Chief Technology Officer /Lead Software Engineer at IZAZI Solutions
This course will provide a conceptual overview and practical hands-on experience of a wide range of key tools, techniques and processes. At the heart of the data mining toolkit is the suite of predictive modelling methods. Accordingly, the course will develop attendees' literacy in the strengths, characteristics and correct application of a range of predictive modelling methods, from relatively simple linear models through to complex and powerful Random Forests, Support Vector Machines, Decision Trees, Gradient Boosting Machines and Neural Networks will be covered along the way.
It will also teach the correct framing of predictive modelling problems, suitably preparing data, evaluating model accuracy and stability, interpreting results and interrogating models. The two key styles of predictive modelling - operational for targeting and explanatory for insights - will be described and distinguished.
As well as predictive modelling, the course will cover a range of other key data mining tools, including:
- Data exploration and visualisation: univariate summaries, correlation matrices, heat maps, hierarchical clustering.
- Principal Components Analysis - used to segment and interpret multivariate data.
- Cluster analysis - used for customer segmentation and anomaly detection.
- Other "unsupervised" outlier detection tools Frequent item set analysis.
- Association analysis - used in retail market basket analysis and the assessment of risk groupings.
- Link and network analysis visualisation - which provide a simple and compelling way to communicate and analyse relationships, and are commonly applied in forensics, human resources and law enforcement.
- This course will use R as the basic learning tool, utilising a range of R packages, including Rattle, a graphical user interface for data mining in R.
- Participants will be exposed to "Big Data" techniques as applied to machine learning and deployed on Cloud Computing platforms.