Mathficast Software Services Limited

Mathfi-Social ©
Classifier/Predictive AI

A new breed of AI-powered service helping you make decisions within different areas of social networking and sociology by performing binary or multi-class predictions and classifications or sanity checking their existing predictions/classifications. Some examples:

1. Social Networking: Knowing the data features of a certain social media content, for example the subject of a video or media posts, number of words, likes, summary, topic, highlights, title, time of the day, the specific channel, location, country, continents, coordinates, history of audience or subscribers’ engagement within that region and many other potential data features, and knowing which segment/segments of past social media subscribers or users (Segments A, B, C, D, E, F, G, H, I or J) have engaged with those past contents, predict for a new social media content, which audience segment (Segments A, B, C, D, E, F, G, H, I or J) are most likely to engage with that content/post/video so that you can target that segment/those segments.

2. Crime Sociology: Knowing the data features such category of location, town or city, coordinates, the businesses or people have been subjected to the crime in past within that specific time of day, all the past coordinates within vicinity of that location, having macroeconomic parameters of the area, population size, how affluential the area is, and knowing the past crime occurrences in that area (which category of crime A, B, C,D, E, F, G, or H occurred), given that location coordinate and time and date and other relevant information including presence of potential people with criminal records in that area, classify and predict which category of crime A, B, C,D, E, F, G, or H is most likely to happen in that coordinate/location and time?

3. Social Influencers: Knowing the subscribers of channels or audiences of the channels, social influencers’ programs they watch on channels, ads they engaged with in past, location, shopping history, income, credit rating, interests, location, house, car, social networking profile, habits and likes, mobile type or more, and knowing which one of the influencers (A, B, C, D or E) they have followed, decide which one of the influencers (A, B, C, D or E) a new channel viewer will follow or watch?

4. Elections: Knowing the data features of past electors such as parameters that contributed to their churn from a political party to another one, their social media activities and presence, likes, comments, people they follow, how affluential the area is, the crime rate in that area, posts on social media, people followed on social media, elector’s current job, shopping history, income, credit rating, interests, past political interests, news pieces read, locations visited, house, car, social networking profile, channels watched, newspapers purchased, elections participated, mobile type or more, and knowing whether past electors churned from party C’s candidate to political party L’s candidate, predict whether a new elector is going to churn moving from the political party C’s candidate to political party L’s candidate or not.

and any other binary or multi-class classification or prediction use cases related to sociology or social networking.