Machine Learning algorithms are born as a solution to a problem. Once we feel comfortable with a prototype, there is still a long path to its deployment...and it is rarely a smooth one. We would like to share our experience transiting that path.
Market research is embracing insightful new sources of data. Among them, behavioural data is one of the most promising. It has proved to have an edge over survey data by overcoming human memory limitations and lack of sincerity. The challenge, however, in sharing clickstream data with third parties is to avoid violating individual's privacy rights, as defined in the GDPR. To overcome this difficulty, we developed our first "PII Filter", based on an intuitive principle: public web sites can be accessed by anyone; therefore, those URLs should be visited by several people. As a result, a new PII Filter has been developed based on a much more Aristotelic principle, learning from experience. This new PII Filter relies on a supervised predictive classifier: a rule-based algorithm that learns from a labelled data set of URLs.
Speech from Marcello Sasso, ESOMAR Representative for Italy.
Exploring the creation of data-driven buyer personas combining psychographic and demographic data to know who speaks about them.
Exploring the creation of data-driven buyer personas combining psychographic and demographic data to know who speaks about them.
This session is about the evolution of the research demand client-side. It explains how clients are facing the internal dilemma of increasing demand for research vs shrinking budgets. Medium-large companies are internalising the research as much as possible, but the demand is increasing and budgets are low. The solution is to open the research division to the external, to generate new revenues that would help financially sustain the development of the department. In the last two years, several companies, especially in the media industry like SG360, Washington Post and The Economist to name a few, are opening their research department to external clients. During the session, we will present the case of Il Sole 24 Ore.
The media research information about the magazine market-oriented medium has evolved in the sense of scaling up the public-lexicon of its socio-economic characteristics. The information we have today revolves around "who" and "how many" read. And yet, practically, nothing has been done in another field of information about this medium, as important as and involving other developments such as "when", "where", "how" and "how many times". Some behavioral patterns are pointed out, without the support of a more scientific investigation, which gives us the necessary security to better estimate the benefits of each actor's relationship with his magazine. The lack of data of this nature minimizes the perception of the potentialities of the environment, underestimating it simply by disregarding its residual power, permanence, speed, rhythm and involvement. Objective To develop a research project that seeks to reveal all the stages of the reader's relationship with their journals.
The media research information about the magazine market-oriented medium has evolved in the sense of scaling up the public-lexicon of its socio-economic characteristics. The information we have today revolves around "who" and "how many" read. And yet, practically, nothing has been done in another field of information about this medium, as important as and involving other developments such as "when", "where", "how" and "how many times". Some behavioral patterns are pointed out, without the support of a more scientific investigation, which gives us the necessary security to better estimate the benefits of each actor's relationship with his magazine. The lack of data of this nature minimizes the perception of the potentialities of the environment, underestimating it simply by disregarding its residual power, permanence, speed, rhythm and involvement. Objective To develop a research project that seeks to reveal all the stages of the reader's relationship with their journals.
Only comparatively recently has informatics been accepted as a science in its own right and its content and boundaries are still unsettled. In effect, the definition of the term informatics is still being argued between experts both at national and international levels. Without going into a lengthy discussion on the semantic and other distinctions it should be made clear that in this paper, the term is understood as the electronic processing of data within information systems. And, in fact, this paper is concerned with those information systems which form the operative instrument for the organization, processing and retrieval of information itself.