Personalized Communications : A Cross Media tool for the future

Personalized communication is when the marketing message is adapted to each individual by using information from a databaseand utilizing it in the various, different media channels available today. That gives the marketer the possibility to create a campaign that cuts through today’s clutter of marketing messages and gets the recipients attention. PODi is a non-profit organization that was started with the aim of contributing knowledge in the field of digital printingtechnologies. They have created a database of case studies showing companies that have successfully implemented personalizedcommunication in their marketing campaigns. The purpose of the project was therefore to analyze PODi case studies with the main objective of finding out if/how successfully the PODi-cases have been and what made them so successful. To collect the data found in the PODi cases the authors did a content analysis with a sample size of 140 PODi cases from the year 2008 to 2010. The study was carried out by analyzing the cases' measurable ways of success: response rate, conversion rate, visited PURL (personalized URL:s) and ROI (Return On Investment). In order to find out if there were any relationships to be found between the measurable result and what type of industry, campaign objective and media vehicle that was used in the campaign, the authors put up different research uestions to explore that. After clustering and merging the collected data the results were found to be quite spread but shows that the averages of response rates, visited PURL and conversion rates were consistently very high. In the study the authors also collected and summarized what the companies themselves claim to be the reasons for success with their marketing campaigns. The resultshows that the creation of a personalized campaign is complex and dependent on many different variables. It is for instance ofgreat importance to have a well thought-out plan with the campaign and to have good data and insights about the customer in order to perform creative personalization. It is also important to make it easy for the recipient to reply, to use several media vehicles for multiple touch points and to have an attractive and clever design.

Machine Learning Algorithms in Heavy Process Manufacturing

In a global economy, manufacturers mainly compete with cost efficiency of production, as the price of raw materials are similar worldwide. Heavy industry has two big issues to deal with. On the one hand there is lots of data which needs to be analyzed in an effective manner, and on the other hand making big improvements via investments in cooperate structure or new machinery is neither economically nor physically viable. Machine learning offers a promising way for manufacturers to address both these problems as they are in an excellent position to employ learning techniques with their massive resource of historical production data. However, choosing modelling a strategy in this setting is far from trivial and this is the objective of this article. The article investigates characteristics of the most popular classifiers used in industry today. Support Vector Machines, Multilayer Perceptron, Decision Trees, Random Forests, and the meta-algorithms Bagging and Boosting are mainly investigated in this work. Lessons from real-world implementations of these learners are also provided together with future directions when different learners are expected to perform well. The importance of feature selection and relevant selection methods in an industrial setting are further investigated. Performance metrics have also been discussed for the sake of completion.