This paper modeled and predicted the price of High Value Commercial Crop using Bidirectional LSTM algorithm. Price of tomato and squash datasets plus software and hardware requirements were utilized in its development and Root Mean Squared Error, and loss computation was performed as assessment method. Gaining low Root Mean Squared Error and losses indicate accurate prediction capability of the system.

The computed RMSE were 2.07 and 2.04 for tomato and squash respectively.

Losses that started from 0.0553 and 0.0570 for training and test dataset respectively which both finish at 0.0128 for tomato; losses for squash started from 0.0172 and 0.0176 for training and test dataset respectively and finish at 0.0019 for training dataset and 0.0020 for test dataset. Price prediction capability of the system is useful to farmers, farm investors and government agencies as it guides them in decision making.

Thesis (Master of Information Technology)

Includes appendices and bibliographical references.