Shape memory alloys (SMAs), such as NiTi, exhibit phase transformations during cyclic loading, leading to degradation in functional properties like recovery strain and thermal hysteresis, known as functional fatigue. This study proposes an artificial neural network (ANN) approach to model the functional fatigue behaviour of NiTi SMA under partial thermal cycling at constant stress (100 MPa) and varying electrical current (10–17.5 A) across 1000 cycles. A feed-forward backpropagation ANN with two inputs (current, number of cycles) and four outputs (recovery strain, permanent strain, upper cycle temperature, and strain accumulation per cycle) was developed. The ANN achieved a prediction accuracy of 94.3%, indicating its reliability in capturing the complex fatigue response of SMAs.