Business Intelligence and data mining

Part 1) Case: Please identify at least 5 flaws in the proposal and provide explanations and better solutions. A guy scored a cool data-mining-oriented analysis job with Right Media, owned by Yahoo!. Right Media is one of the top two Internet advertisements exchanges in Hong Kong, and delivers over 1 million ad. each day. Mike has been working with engineers from Yahoo Research to design new data-mining-based techniques to better predict click-through-rate (CTR, if you don't know this term, just Google it) for Internet advertisements. The new technique intends to charge differently from the companies who invest on online ad. at yahoo.com.hk., given the different estimated probabilities of CTR. The idea is that the higher the estimated CTR is, the more Right Media would charge for displaying the ad.. Mike is now writing a short proposal about this project. Details of the proposal can be found in the attached file. Part 2) You will need to use Weka to convert the textual data (emails) into feature vectors and build text mining models for automatic spam filtering. The email messages you will use were delivered to a particular server between 8 Apr 2007 and 6 Jul 2007. The target variable represents whether an email is either ham (non-spam) or spam. Other details and datasets can be found in the attached files