Helpdesk Ticket Classification for Technician Assignment Routes Using BiLSTM

Fast problem-solving is one of the main keys to a company's reputation. Currently, most business processes are accommodated by applications. Often, applications in companies experience problems due internal and external factors. Users send request solve submitting problem helpdesk tool or application. The requests at application do not go directly technician who has authority them but instead operator first then escalate be resolved. This process affects efficiency time. study proposes use text classification with deep learning complete work. method proposed this BiLSTM method. total data used research 160,000 dividing 128,000 resolved as training 32,000 on-progress testing 80% 20% data. was conducted using 13 labels for assignment route Performance measurement confusion matrix which obtained an accuracy 91.18%, precision 95.05%, recall 93.28%