A Data Science Central Community
We use linear scaling to calculate score/points for an applicant. Now, if we were to determine the number of points for each attribute of a characteristic, Naeem Siddqui, gives the following equation (Image attached).
I understand that it is nothing but dividing the total # of points into each attribute of each characteristic which is why we are dividing the offset and the intercept term by number of characteristics, however, what perplexes me is the negative term.
ln(odds) has been replaced by the logit equation with a negative term outside the bracket. I am unable to understand from where did the negative sign appear.
If anyone has an idea then please advise.
I presume that the negative sign is simply due to the fact that most definitions of WOE define it as ln(%Goods/%Bads) while the score is proportional to ln(odds), where odds is usually defined as Probability(Bad) / Probability(Good) in risk models... Therefore score ~ -WOE.
I would suggest checking the context where you found this formula to check if this is actually the case.