In doubly selective channels, receiver windowing constitutes an effective technique for enhancing the banded structure of the frequency-domain channel matrix, and thus improving the effectiveness of a banded equalizer for intercarrier interference (ICI) mitigation. A common window design technique, which performs close to optimal, is based on the criterion of maximum average signal-to-interference-plus-noise ratio (SINR). The optimality of this technique has been verified for stationary channels with perfectly known statistics. However, in cases where this assumption does not hold, a near optimal performance can be achieved at the expense of high complexity cost. To overcome these limitations, an adaptive windowing technique is proposed that is able to track the optimal receiver window offering low-complexity requirements. Through simulation experiments it has been verified that the proposed technique is able to adapt to the varying channel statistics with increased robustness to channel modeling errors.