K.Krishna,M.Sravanthi,M.Mrudula,M.Vamsi Priya,Emani Sri Lakshmi,Dr.G.Sravanthi 02 07 The primary audience for sellside analysts recommendations is institutional investors that are required to invest in a broad range of companies within clientmandated equity benchmarks like the FTSEJSE AllShare index It might be difficult for portfolio managers to make unbiased investment judgements given the various sellside recommendations for a single stock Using random forest extreme gradient boosting deep neural networks and logistic regression this study investigates the utilisation of past sellside recommendations to produce an impartial fusion of analyst forecasts that optimises bidirectional accuracy While eliminating forwardlooking biases we incorporated 12month rolling features derived from common sellside recommendations such as analyst coverage point and directional accuracy By combining forecast features from many analysts using machine learning techniques we introduce a novel AI analyst By methodically producing objective and incrementally better prediction accuracy from publicly available sellside recommendations we were able to observe the additional benefits of using these features from multiple analysts The Decision Tree algorithm XGB Random forest and KNeighbors algorithms demonstrated the highest relative performance Machine learning algorithms perform better in resourcerelated industries with high volatility than in industries with low volatility indicating the value of rolling features in bidirectional prediction under such conditions We observe the incremental contribution of rolling features using feature significance illuminating the connections between analyst coverage volatility and the accuracy of bidirectional forecasts Furthermore when modelling analysts directional forecasts factors using logistic regression highlight volatility features initial and target price as some of the crucial aspects Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026