A number of logistic, financial and administrative challenges make it difficult collect adequate and suitable data in order to apply classical fisheries management strategies. Consequently, the more data intensive classical fisheries biological and economic (bio-economic) models do not provide adequate and reliable analytical results for fisheries management. Alternative models are required to deal with the data poor situations in Lake Victoria but also to provide a robust approach to fisheries modelling. The surplus production model provided the only target reference point mentioned in the Law of the Sea Convention, the Maximum Sustainable Yield (MSY), which until the 1970s was regarded in most world areas as the appropriate target for management. The broad generality provided by this simple biomass model allowed early application of economic theory (Gordon, 1954) and led to the Maximum Economic Yield (MEY) as a ‘target reference point’ to the left of MSY on the fishing effort axis. The objective of this study was to demonstrate that data poor fisheries can still be modelled using Artificial Intelligence (AI) and Machine Learning Algorithms such as supervised feed-forward Artificial Neural Networks (ANN) and Time Series Decomposition/Analysis to demonstrate that ex-vessel fish value depends on the fish species, biomass and foreign exchange rate over time. The main aim of the study was to analyze monthly fish value of the major commercial species to determine which species have significant impact on the total fish value from Lake Victoria (Kenya), determine the cyclic movement and trends as an alternative to the data intensive classical fisheries bioeconomic models such as Gordon Schaefer. The application of AI and ANN do not mot make any assumptions about any model and uses the data to learn, test and validate the network, thereby eliminating the need for pre-determine model, while Time series decomposition/Analysis resolves the long term data into its cyclic, trend and irregular movements in order to determine composite annual indices of fish value on monthly basis and offers potential for future predictions.