For the end of 2011, many around the blogosphere are forecasting what will be on hype next year. I often read that big data and mobile BI are on the hype. In this article, I will discuss about those technologies. Don’t believe the ads, those technologies aren’t game changer at all.
Measuring and managing return on marketing investment, that’s the promise of the book from Guy R. Powell. A famous quote in marketing is : Half of my advertising is wasted; I just don’t know which half (John Wannamacher). Indeed, how many marketing initiative are rigorously evaluated? No doubt price cuts increase volumes, but how often does it to improve the top line, not even talking about the bottom line. This book is about putting some analytics in marketing and knowing the truth.
My last post discuss about SQL queries. Nevertheless, sometimes data came from differents databases. In such cases, it is no longer possible to use SQL. ETL tools, which stands for Extract Transform Load are designed to easilly allow data transformations. I have currently used three tools : Talend, SAP Business Objects Data Integrator and Kettle. I will review them and explain one or two tips I’ve learned using ETL tools.
Data manipulation is a big part of a data mining process. Some authors claims it could take 80% of a data mining project. I could only agree. If data comes from the data warehouse it could be a lot faster. If you have to dig (and understand) operational systems or adding some externals data the works takes even more time. Therefore it is of greatest importance to be efficient in data manipulation. Currently I use two way to do this task : big SQL queries or ETL depending on the situation.
When deploying a model, one very important thing is to monitor the results. Does it work like you’ve expected? I’m not talking about pre production tests but following the life of your model. I use two kind of reports to do that : preventive reports and corrective reports. As you expect the first one is created just after the prediction and the second is created after the consequence of the prediction is known.