HS Code Recommender

Our project is to classify the specific HS code for the importer or exporter that he/she wanted to trade for. Harmonized Systems (HS): The Harmonized System is an international nomenclature for the classification of products. It allows participating countries to classify traded goods

Project Title

HS Code Recommender

Project Area of Specialization

Artificial Intelligence

Project Summary

Our project is to classify the specific HS code for the importer or exporter that he/she wanted to trade for.

Harmonized Systems (HS):

The Harmonized System is an international nomenclature for the classification of products. It allows participating countries to classify traded goods on a common basis for customs purposes. At the international level, the Harmonized System (HS) for classifying goods is a six-digit, eight-digit and ten-digit code system. 

The HS comprises approximately 5,300 articles/product descriptions that appear as headings and subheadings, arranged in 99 chapters, grouped in 21 sections. The six digits can be broken down into three parts. The first two digits (HS-2) identify the chapter the goods are classified in, e.g. 09 = Coffee, Tea, Mate, and Spices. The next two digits (HS-4) identify groupings within that chapter, e.g. 09.02 = Tea, whether or not flavored. The next two digits (HS-6) are even more specific, e.g. 09.02.10 Green tea (not fermented)... Up to the HS-6 digit level, all countries classify products in the same way.

https://unstats.un.org/unsd/tradekb/Knowledgebase/50018/Harmonized-Commodity-Description-and-Coding-Systems-HS

Project:

We will build a back-end engine that asks different questions from the user and tells them their respective HS code. We will train this engine by Artificial Intelligence concepts on a large amount of data related to the HS codes. The engine will also learn from the answers of users and on runtime, it decides the next question be asked and with the continuation of this process, it will finally classify the desired HS code of the user.

This project will help both the custom department and the importer or exporter to classify the desired HS codes within minutes.

Project Objectives

The goal of this project is to develop a back-end engine that recommends the specific HS codes to our users on behalf of the items which they wanted to export or import. Our project will mainly focus on the following objectives:

1. Develop a system that automatically and regularly collects and correlates data for HS codes using the information of importer or exporter items that are available on the internet.

2. Build a database of different types of questions that are being derived from the information related to HS codes.

3. Utilize text mining techniques to find desired HS codes according to certain personal preferences.

4. Our back-end engine will be integrated with the customs department website so that whenever any importer or exporter comes to do trade; our system helps them in finding their desired HS code.

To achieve the first goal, we will collect data from the internet i.e., from the custom department website. They provide 90 days of data on their website.

To achieve the second goal, we will use machine learning techniques such that every next question will be derived from the answer of the user respectively.

To achieve our third goal, we will study and implements different text mining algorithms.

The biggest challenge we expect to face will be recommending the specific HS code because there are approximately 5000 commodity groups of HS codes respective to the items. To address this challenge, we will use algorithms that uses user’s information related to items being imported or exported. Also, we will use text mining techniques with the help of different algorithms in order to extract information from the description that the user given to us.

Project Implementation Method

1. Write the proposal.

2. Do the literature survey.

3. Do research on different HS Codes which is based on 99 chapters.

4. Collection of data.

5. Study different text mining algorithms.

6. Study different machine learning techniques.

7. Structuring the database.

8. Develop text mining algorithms.

9. Develop machine learning algorithms and techniques.

10. Develop engine for the recommendation.

11. Test the collection of data.

12. Test the database.

13. Test the algorithms.

14. Test the engine functionalities.

15. Write monthly reports.

16. Write progress reports.

17. Write a final report.

18. Make a project video.

19. Prepare for the presentation.

20. Design the project poster.

Benefits of the Project

To ensure harmonization, the contracting parties to the Convention on the Harmonized Commodity Description and Coding System, have agreed to base their national tariff schedules on the HS nomenclature and Legal Notes. Parties are permitted to subdivide the HS nomenclature beyond 6-digits and add their own Legal Notes according to their own tariff and statistical requirements. Parties often set their customs duties at the 8-digit "tariff code" level. Statistical suffixes are often added to the 8-digit tariff code for a total of 10 digits.

HS Chapter 77 is reserved for common use by the parties internationally. Chapters 98 and 99 are reserved for national use. Chapter 98 comprises special classification provisions, and chapter 99 contains temporary modifications pursuant to a parties' national directive or legislation.

Since its creation, the HS has undergone several revisions - ostensibly, to either eliminate headings and subheadings describing commodities that are no longer traded or to create headings and subheadings that address technological advancements and environmental concerns. The current version of the HS became effective on January 1, 2017.

In our final year project, we similarly perform data/text mining to recommend HS Codes to the importer or exporter.

Technical Details of Final Deliverable

1. Collection of data

2. Training of data of HS Codes

3. Prepare data for questions

4. Train model by using machine learning

5. Train model by using text mining techniques

6. Train AI model

7. Testing of data

8. Testing of algorithms

9. Training on user’s answers

10. Recommendation according to the user’s answer

11. Show response

12. Develop Backend Model

13. Deploy Backend

14. Show correct result

     15. Train AI model

     16. Training on user’s answers

     17. Recommendation according to the user’s answer

     18. Develop Backend Model

     19. Deploy Backend

     20. Show correct result

Final Deliverable of the Project

Software System

Core Industry

Others

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Decent Work and Economic Growth

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com