Classifiers, such as artificial neural networks non-linear equaliser (ANN-NLE), Wiener–Hammerstein non-linear equaliser, Volterra non-linear equaliser (Volterra-NLE) and support vector machine non-linear equaliser (SVM-NLE), can play a significant role in compensating non-linear imperfections in the optical communications context. Using classifiers to mitigate the non-linear effects in coherent optical orthogonal frequency division multiplexing (CO-OFDM) systems is an interesting idea to be investigated. In this study, a novel support vector machine robust version, specifically adapted to a 100 Gb/s CO-OFDM data structure for long haul distance, is proposed. Firstly, the authors demonstrate that SVM-NLE upgrades the system performance by about 10−1 in terms of bit-error rate compared to Volterra-NLE at optical signal-to-noise ratio equal to 14 dB. Then, they show that it can double the transmission distance up to 1600 km over single mode fibre channel. Furthermore, a performance comparison is performed using 16 quadrature amplitude modulation and 40 Gb/s bit rate for SVM-NLE, ANN-NLE and inverse Volterra series transfer function non-linear equaliser, respectively.