AiPaS - Apparel Industry Performance Analysis Software


Table of Contents

  1. Introduction
  2. Problem
  3. Proposed Solution
  4. High Level Solution Architecture
  5. Data Flow
  6. UI Designs
  7. Supervisors
  8. Links


The second-largest source of income in Sri Lanka is the apparel industry. While lots of companies in this industry are gradually adopting new technologies like smart quality management systems, even some of the largest companies in Sri Lanka are still taking a very traditional approach in their product management. Even the slightest improvement in the efficiency and reliability of this process with seamless integration of new technologies like Big Data and ML could go a long way in strengthening the Sri Lankan economy. There is no better place than Hirdaramani Apparel, the third largest and the oldest apparel exporter in Sri Lanka, to take a big step in this direction. The possibility to make a contribution to such a shift is thrilling, especially with a project that has virtually no cost, yet promising results.


Proposed Solution

To develop an application that allows the user to load datasets and see meaningful information and visualizations in an easy-to-understand manner. Administrators will be able to pay attention to the underlying causes of low OTD by identifying them with the application. Furthermore, it can predict the OTD based on the fields involved.

The business value of the solution

How is the solution better than the existing one?

High Level Solution Architecture



The front end of the application lets the user to


The backend of the application

Passes the raw data in the files to the backend. Obtains data necessary for visualizations.

Data Flow


Data input

The input data file is first parsed and stored in our data structure. That way, we can switch between various input files without propagating that change into the other components in our system. For example, if the client requirements change for the input file from an excel file to a CSV file. Then, it can be implemented easily by replacing the parser with a suitable implementation.


The data is stored to make our system stateful by avoiding repetitive uploads of the same file. Next in the data pipeline is the machine learning model. That consists of both the model training and predicting components. The machine learning model is implemented in a modular way to achieve low coupling.


The predicted and input data can be visualized in the user interface. At this stage of the data pipeline, we use a cache for storing predicted data in the front-end to provide faster loading times for the user.

UI Designs

user-home custom-analysis add-graph factories …..