Make Better Decisions with Big Data People


A character is an imaginary figure representing a segment of real people, and it is a communicative design technique aimed at improving the user’s understanding. Over decades of use, personas were data structures, user attributes of static frameworks without interactivity. A persona was a way to organize data about the imaginary person and present information to decision makers. It wasn’t really workable in most situations.

How personas and data work together

With the increase in analytical data, personas can now be generated using big data and algorithmic approaches. This integration of personas and analytics offers powerful opportunities to move personas from flat data presentation files to interactive interfaces for analytics systems. These persona analysis systems provide both the empathic connection of the personas and the rational perspectives of the analysis. With persona analysis systems, the persona is no longer a static, flat file. Instead, they are operational modes of accessing user data. The combination of personalities and analytics also makes user data less difficult to use for those who don’t have the skills or desire to work with complex analytics. Another advantage of persona analysis systems is that one can create hundreds of data-driven personas to reflect the various behavioral and demographic nuances of the underlying user population.

A “personas as interfaces” approach offers the advantages of both personas and analysis systems and addresses the shortcomings of each. Transforming both the process of persona creation and analysis, personas as interfaces have both theoretical and practical implications for design, marketing, advertising, healthcare, and human resources, among other areas.

This persona as interface approach is the foundation of the persona analysis system, Automatic Persona Generation (APG). Pushing the advancements in the conceptualization, development and use of personality and analysis, APG features comprehensive multi-layered integration offering three levels of presentation of user data, which are a) conceptual personality, b ) analytical measurements, and c) fundamental data.

APG generates persona casts representing the user population, with each segment having a persona. Relying on regular data collection intervals, data-driven personalities enrich traditional personality with additional elements, such as user loyalty, sentiment analysis and topics of interest, which are features requested by APG customers.

By leveraging intelligence system design concepts, APG identifies unique behavioral patterns of user interactions with products (i.e., they can be products, services, content, interface features, etc.), and then associate those unique patterns with demographic groups based on the strength of the association. the unique model. After obtaining a clustered interaction matrix, we apply matrix factorization or other algorithms to identify the latent user interaction. Matrix factorization and associated algorithms are particularly suitable for reducing the dimensionality of large data sets by discerning latent factors.

How APG Data-Driven Personas Work

APG enriches the user segments produced by algorithms by adding name, image, social media comments and appropriate demographic attributes (e.g. marital status, education level, occupation, etc. ) by querying the audience profiles of the main social media platforms. APG has an internal meta-tagged database of thousands of purchased copyright photos that are appropriate for age, gender and ethnicity. The system also has an internal database of hundreds of thousands of names that are also appropriate for age, gender and ethnicity. For example, for the character of an Indian woman in her twenties, APG automatically selects a name that was popular for women twenty years ago in India. The characters based on the APG data are then displayed to the users of the organization through the interactive online system.

APG uses the fundamental user data on which the algorithms of the system act, transforming this data into information about the users. This result of algorithmic processing consists of metrics and actionable measures regarding the user population (i.e. percentages, probabilities, weights, etc.) of the type that would typically be seen in software packages. industry standard analysis. The use of these actionable metrics is the next level of abstraction adopted by APG. The result is a personality analysis system capable of presenting information about users at varying levels of granularity, with levels that are both built-in and task-appropriate.

For example, C-level executives may want a high-level view of users for whom personas would be applicable. Line managers may want a probabilistic view for which analysis would be appropriate. Implementers should take direct user action, such as a marketing campaign, for which individual user data is more relevant.

Each level of the APG can be broken down as follows:

Conceptual level, personas. The highest level of abstraction, the conceptual level, is the set of personas that APG generates from the data using the method described above, with a default value of ten personas. However, APG can theoretically generate as many personas as needed. The character has almost all of the typical attributes found in traditional flat file character profiles. However, in APG, personas as interfaces allow for significantly increased interactivity by leveraging personas within organizations. Interactivity is provided such that the decision maker can change the default number to generate more or less personas, with the system currently configured for between five and fifteen personas. The system can be used to search for a set of personas or to use analytics to predict the interests of personas.

Level of analysis: percentages, probabilities and weights. At the analytical level, APG personas act as interfaces to the underlying information and data used to create the personas. The specific information may vary somewhat depending on the data source. Nevertheless, the level of analysis will reflect the metrics and metrics generated from the fundamental user data and create the personas. In APG, personas provide access to various analytical information via clickable icons on the persona interface. For example, APG displays the percentage of the entire user population that a particular character represents. This analytical information is valuable for decision makers in determining the importance of design or development for a specific character and helps to address the issue of character validity in portraying actual users.

User level: individual data. By tapping into the demographic metadata of the underlying factorization algorithm, decision makers can access the specific user level (i.e., individual or aggregate) directly in APG. Digital user data (in various forms) is the foundation for personas and analytics.

The implications of data-driven personalities

The conceptual change of personas from flat files to personas as interfaces for better user understanding opens up new possibilities for interaction between decision makers, personas and analytics. By using data-driven personalities embedded as interfaces to analytics systems, decision makers can, for example, imbue analytics systems with the benefit of personas to form a psychological bond, via empathy, between stakeholders. and user data and always have access to practical information. user numbers. There are several practical implications for managers and practitioners. Namely, personas are now actionable because personas accurately reflect the underlying user data. This aspect of full-stack implementation was not previously available with personas or analytics.

APG is a fully functional system deployed with real customer organizations. Please visit https://persona.qcri.org to see a demo.

This content was written by Qatar Computer Research Institute, Hamad Bin Khalifa University, member of the Qatar Foundation. It was not written by the editorial staff of MIT Technology Review.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *