Fuzzy rule interpolation (FRI) predicts an accountable outcome of a possible course of action in sparse fuzzy rule base system (FRBS). However, in real life, we encounter some situations where the antecedent has to be predicted to obtain a desired consequent of FRBS. In this situation, inverse fuzzy rule interpolation (IFRI) or backward fuzzy rule interpolation (BFRI) is used to get the desired outcome. Here a geometry based inverse fuzzy rule base interpolation (GIFRI) is suggested. The mathematical detail of the proposed method is elaborated and its geometrical interpretation is given with the help of fuzzy geometry. It is to be noted that the proposed method ensures that the inverse of the inverse is the original one.