K-nearest Neighbour is a non-parametric, versatile, and supervised machine learning (ML) algorithm used to perform regression analysis and classification by identifying data points that are similar and near each other in feature space. Our research identifies that the K-nearest Neighbour Algorithm Clustering Simple Moving Average (KNN SMA) outperforms the current standardised simple moving averages (SMA), 9, 21, 50 and 200. Even though the KNN SMA is a profitable indicator after optimisation, it is essential to note that one indicator alone will not be suitable for managing a portfolio strategy. It is also necessary to understand that when using algorithmic development, the strategies created do alpha decay faster than standardised indicators, namely the 9, 21, 50 and 200 SMA. This research analyses the findings of the KNN SMA in comparison to the 9, 21, 50 and 200 SMA. The study also provides insights into possible methods of incorporating the KNN SMA into the portfolio as a trend component. It is important to note that most traders are unprofitable due to qualitative judgements and cognitive biases, so using a quantitative approach for trend classification is advised. The KNN SMA benefits retail investors as it’s an algorithmic strategy that can be operated through TradingView, optimised and backtested on any computers with access to the TradingView Assistant.