Analytics and Data Summit 2018

Long gone are the days when mass mails with the same message and offer were sent to all customers. With the amount of data companies have on their customers together with tools such as Oracle Advanced Analytics a new world of possibilities for personalized and proactive marketing opens up. A company with customer data in an existing datawarehouse built on Oracle databases have a short time to market for an advanced analytics platform using the licensed option of Oracle Advanced Analytics. In this session I will go through the learnings along the way from being reactive to proactive using the whole offering of R together with Oracle Advanced Analytics to empower data scientists and analysts to generate cutting edge customer insights inside the database.

This presentation focuses on unlocking the power of Data Science for data-driven decision support. It details the pragmatics of using Machine Learning techniques in OBIEE for actionable BI and Predictive Analytics from a business standpoint. Two industry use cases are presented to illustrate the implementation of the same using OBIEE 12c.

Real life Manufacturing Data is not like iris or titanic. We cannot just .fit() and .score(). We need to effectively .transform() the data. In this presentation, we will look at the complexity of manufacturing data and various ways to feature engineer manufacturing data to derive meaningful variables to solve manufacturing problems. Specifically we will look at a. Methods to construct machine learning data set for different type of Manufacturing like Lot Controlled, Serial Controlled, Batch Manufacturing, Discrete Manufacturing b. Transformation method of time series data from Machine Sensor Readings c. Various binning transformations on transaction data

Oracle Marketing Advanced Analytics team has been using Oracle R Enterprise(ORE) for propensity to buy modeling for the past few years. We have recently expanded our use of ORE to event registration. The models allow Oracle to target the right contacts for email marketing for product events. We have shown up to 4X increase in registration rates from model targets over the baseline. The presentation will cover an overview of the results of our modeling as well as some key insights we have learned on how to model using ORE.