Abstract— Every year, the Faculty of Engineering at Nurul
Jadid University forms a committee to manage the process of
students' final projects from the title selection stage to the final
examination process until graduation. The process of selecting the
final project title is still done manually, namely by checking the
titles one by one, which takes a long time and allows errors because
there is a lot of data to check, so human errors can also occur.
Therefore, this research proposes to use the Bidirectional Long
Short Term Memory (BiLSTM) method to classify the final
project title based on its grade category. Several experiments were
conducted to generate the most appropriate labels. The first
experiment produced 4 labels and the second experiment
produced 2 labels. From the results of several experiments, it was
concluded that the second experiment had the best accuracy
results with the 'good enough' and 'good' classes. The
oversampling technique was then applied to overcome overlapping
data, and the turning process was then performed on several
parameters that could re-optimize the previous accuracy result of
75.24% to 91.15%. With a configuration of 10 random state
parameters, using 64 batch sizes and 50 epochs. In addition, model
adjustments were made to the hidden layer by adding a dropout
layer and relu activation.