Customer ticket prediction

Keywords: Customer, ticket

Background

For the purpose of forecasting consumer ticket behavior, an (ANN) model was created. Both historical ticket data and information about consumers were included in the collection. Using a binary classification strategy, a sigmoid activation function, binary cross-entropy loss, and an Adam optimizer, the ANN model was trained and evaluated. The model had an accuracy of 80% on a test dataset after iterative improvement. Handling values that are missing, treating outliers, and scaling features were all included in the preprocessing processes. The created model exemplifies ANN's capability to predict consumer ticket behavior with accuracy. This study helps improve ticket processing procedures and management of customer service, ultimately leading to higher satisfaction among customers.

Aim & Objectives

Aim
To Predict the Customer Ticket Using DL Techniques
Objective

Develop an ANN model for precise customer ticket prediction, optimizing issue resolution and service efficiency.
Investigate ANN configurations to enhance ticket prediction accuracy, accommodating various customer concerns and inquiries.
Evaluate the ANN's performance in predicting customer ticket outcomes, ensuring valuable insights for service improvement.

Research Methodology

ANN Technique used

Software & Tools

Jupyter, Google Collab

— Preview truncated. The complete document (full chapters, references, diagrams, and appendices) is shared with clients as part of project delivery. —