Oraclum Intelligence Systems Ltd (henceforth Oraclum) is a non-partisan start-up based in Cambridge, interested in experimental testing of forecasting models on real-life electoral data. We aim to use the Bayesian Adjusted Social Network (BASON) Survey of US voters to try and pick out the most precise prediction method in light of the upcoming US Presidential elections, using the power of social networks. For more details regarding the logic behind our method please see here
UX Passion is collaborating on this project. UX Passion is a UX design, usability and product development agency with the global reach. One of the verticals within the firm is data analytics and visualisation, and those specialities are utilised in this project where UX Passion was in charge of design and front-end development.
Given the experimental nature of the survey in its current phase, there are no immediate financial interests that Oraclum or UX Passion stand to gain from it. The survey is financed entirely by Oraclum and, at its current stage, is not profit-oriented. We do however hope to develop the method into a proper bias-adjusted social network survey which will later be used for commercial purposes.
The survey will run up until Election Day (November 8th) when we will provide our final forecast. Our forecasts will show the electoral votes, the total predicted percentages, and the probability distributions for two main candidates, all presented on the map of US states. They will also show the distribution of preferences for the friends of each user (so that the user could see how his or her social network is behaving and who they, as a group, are voting for), and the aggregate predictions the survey respondents will be giving.