Method of website optimisation for a website hosted on a server system, and a server system

A computer implemented website optimisation system for website optimisation of a website hosted on a server system, the website for use by a plurality of users, the computer implemented website optimisation system including the server system, the server system running computer software configured to:

• (i) collect data for constructing a plurality of user profiles corresponding to the plurality of users;
• (ii) construct the plurality of user profiles using the collected data;
• (iii) quantify affinities between the plurality of user profiles;
• (iv) construct a user network, in which users are represented as nodes, and in which the affinities are represented as links between the nodes;
• (v) construct an adjacency matrix which describes the network;
• (vi) calculate a first principal eigenvector of the adjacency matrix;
• (vii) define a new network by removing a random link in the network and calculate a new adjacency matrix for the new network;
• (viii) calculate a second principal eigenvector of the new adjacency matrix;
• (ix) calculate a vector of relative shifts between the first principal eigenvector and the second principal eigenvector;
• (x) for every node, assign a value for a direction of its shift between the network and the new network;
• (xi) repeat (vii) to (x) for a plurality of links;
• (xii) calculate a node affinity matrix;
• (xiii) assign nodes to different communities using values of elements of the node affinity matrix, to segment the user network into a plurality of communities of users, and
• (xiv) provide website content to each user according to the segmented community of each user.

A server system hosting a website for use by a plurality of users, the server system running computer software configured to:

• (i) collect data for constructing a plurality of user profiles corresponding to the plurality of users;
• (ii) construct the plurality of user profiles using the collected data;
• (iii) quantify affinities between the plurality of user profiles;
• (iv) construct a user network, in which users are represented as nodes, and in which the affinities are represented as links between the nodes;
• (v) construct an adjacency matrix which describes the network;
• (vi) calculate a first principal eigenvector of the adjacency matrix;
• (vii) define a new network by removing a random link in the network and calculate a new adjacency matrix for the new network;
• (viii) calculate a second principal eigenvector of the new adjacency matrix;
• (ix) calculate a vector of relative shifts between the first principal eigenvector and the second principal eigenvector;
• (x) for every node, assign a value for the direction of its shift between the network and the new network;
• (xi) repeat (vii) to (x) for a plurality of links;
• (xii) calculate a node affinity matrix;
• (xiii) assign nodes to different communities using values of elements of the node affinity matrix, to segment the user network into a plurality of communities of users, and
• (xiv) provide website content to each user according to the segmented community of each user.