VINIF.2020.DA11 – Big Data Analytics for Vietnamese Overseas (BDAVO)

Principle Investigator
Dr. Pham Xuan Lam
Host Organization
National Economics University

More than 5 million Vietnamese people have been living and working in many places around the world with many highly qualified and influential intellectuals and experts. This is a valuable resource for the country’s development and integration process. BDAVO focuses on synthesizing and processing data from many sources in exploiting and connecting Vietnamese and Vietnamese-origin talent abroad. The project researches and applies some technologies of Big data, Data mining, Data analytics, Machine learning… to create a platform that contributes to building resources for the Innovation Ecosystem in Vietnam.

Some research and application directions in the BDAVO project:

  • Collect from many sources
  • Extract and process unstructured data
  • Parallel storage and processing on cloud computing
  • Big data mining, machine learning, and clustering
  • Smart search and suggestion
  • User-friendly information, interface display

BDAVO will be the “core” technology for the VietSearch application ( with the goal of being a search engine for Vietnamese data outside of Vietnam (Vietnamese people, Vietnamese companies, Vietnamese events) to connect effectively between people in need and service providers around the world. VietSearch aims to be a global “Exploitation of Vietnamese knowledge” platform in the fields of science, technology, education, economics, charity, health…

The project’s research and application goals include:

  • Develop a number of algorithms, knowledge systems, and open data sets in the field of detecting and searching for global Vietnamese experts and services;
  • Cooperate and introduce Vietnamese experts abroad for domestic events and research activities;
  • Search for high-level human resources with appropriate expertise, helping Vietnamese businesses expand markets and cooperate internationally;
  • Connect, suggest and introduce experts and services of overseas Vietnamese to Vietnamese people studying, working, traveling… abroad;
  • Support the government and Vietnamese diplomatic agencies abroad in community development and connecting overseas Vietnamese.


Principle Investigator
Dr. Pham Xuan Lam
Host Organization
National Economics University


Expect Progress
Phase 1

– Collect data about industries, positions, expertise, services, leading universities, research institutes, and businesses in the world (DataCollection)
– Collect data from experts from public data sources (DataCollection)
– Develop an algorithm to detect Vietnamese experts (VietNameDetection), classify expert data by profession
– Develop expert ranking algorithm (VietExpertRank)
– Developing a distributed big data processing system (DataPipeline)
– Integrate into VietSearch system
– Research and build models to represent expert knowledge using ontologies. VietExpertOntology
– Support training of 1 graduate student

Phase 2

– Improved distributed big data processing system (DataPipeline)
– Improved information extraction and Expert classification functions (DataCollection)
– Improved VietExpertRank
– Develop a system to suggest experts by field and event VietExpertMatch
– Improve search features and suggest experts using VietExpertOntology.
– Integrate into VietSearch system
– Publishing scientific reports

Phase 3

– Complete data, experiments and publish scientific reports
– Support training of 1 PhD student
– Complete VietSearch’s features: manage users, edit interface, set up monitoring, alert, deployment systems.
– Building a business model for VietSearch system