Simple score function with 4 different indicators

I want to create a function, which returns a value between (0,1) or (-1,1). The result of this function is then used for a boolean decision. E.g. if the value is closer to 0 decision D1 is made, if it is closer to 1 decision D2 (a threshold needs to be defined). The function is based on 4 indicators that are normalised (all values represent a percentage). My question is now, how can I combine the 4 indicators to create a composite value.

My first simple try is:

V = (W_A * A + W_B * B + W_C * C + W_D * D) / 100

Explanation of the variables:

V ... is the decision result
W_X ... is the weight
W_A + W_B + W_C + W_D = 1
A, B, C, D ... the indicator values

The problem is that two values A and B have a negative influence on the composite value. That is, if A or B is higher, V should be lower and if A or B is lower V should be higher. For C, D, if they are higher, V should be higher.

My first idea was to use negative values for A and B. But if they are close to 0, V should be higher. Another, perhaps better approach is to use the inverse form of A and B. That means 1-A and 1-B.

Are there any better ideas?

Topic score correlation evaluation

Category Data Science

About

Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.