What is the Microsoft Azure Virtual Hackathon?

This virtual hackathon aims to bring together AI/ML enthusiasts, talented developers, designers, and entrepreneurs to solve real-world business challenges from APAC using Azure AI. With multiple partner challenges, our goal is for participants to use Azure technology to create something innovative and transformative. The hackathon will be broken up into two phases. Phase 1 will consist of solution design and architecture. Phase 2 will consist of taking your idea and creating a prototype.

Winners Announcement

Hakk.ai – HakkTaxi is a taxi hailing app that allows users to book a taxi from any location to the desired destination. The mobile app was created to test the developed API and to simulate its real world use.

AgroVision – AgroVision is an integrated farm health management tool that leverages machine learning and IoT to improve the yield and quality of urban farms in high-density cities.

In an urbanised landscape like that of Singapore, the path to self-sufficiency lies in building-integrated agriculture. While urban farming is promising, the incursion of weed and disease remains a challenge. Agrovision combines the state of the art in ML and IoT technologies and delivers a comprehensive solution to the farming community. It not only enables early weed detection and assessment of abnormal plant health, but the data is further used to suggest actionable strategies and counter-measures. Moreover, AgroVision provides extended analytics on aggregated data for policy-makers to steer the country towards sustainable urban farming.


Each team may submit one submission for every challenge


Grab is Southeast Asia’s leading ride-sharing company. Millions of passengers arrive at their destinations safely everyday via Grab’s services.

Estimated time of arrival (ETA) on the way towards pickup or destination plays a crucial role in order to provide excellent travel experience to our customers.

An accurate prediction of travel times, reduces passenger anxiety before the ride helps them in managing their time better. Additionally, Grab can leverage accurate ETAs to maximize efficiency of allocation as well as make fair pricing for each trip. In this hackathon, we would like to pose the problem of predicting estimated times of arrival given GPS trails from thousands of trips fulfilled by Grab.

This can be achieved by developing a machine learning model either dependent on the route or otherwise.


Given Singapore’s limited size and strong competition between different types of land use, agricultural land is now less than 1% of overall land use.

In recent years, the city state has also been looking to alternative spaces that can optimise under-utilised spaces within the city, such as rooftops, for food production.

As more entrepreneurs recognise the opportunity and consumers behaviour changing, urban farming has been gaining traction. Given its unique context, challenges and opportunities, Singapore has announced an ambitious target (“30 by 30”) of reducing its reliance on imports and to produce 30% of its nutritional needs domestically by 2030 – a significant increase from the current less than 10% share.

Food from urban farms present sustainable opportunities as they require less time and carbon miles to transport to the market, and can meet the rising demand of health- and environmentally- conscious consumers for fresher food with a lower carbon footprint. Their visibility in the city also piques interest among young professionals in food production. Urban farming is thus a budding sector in Singapore, and spurred by its “30 by 30” goal, push and support systems for startups and SMEs.

However, the incursion of pest and disease is a challenge for agriculture, especially for urban farms.

There are limited options for control as a majority of conventional crop protection methods such as pesticide spraying might not be applicable due to close proximity to the community. Given the emerging threats from new crop pests and diseases (e.g. fall armyworm) and the growing demand for production of fresher produce with lower carbon footprint within cities, there is a need for suitable solutions that are safe, effective and environmentally friendly to minimise crop loss caused by pest and disease in urban farms.

UNDP problem statement details.
UNDP dataset


3,000 USD for the winning team of each challenge

1. Surface tablets for all members of the 1st Prize winning team

2. Eligible candidates to be selected for an interview opportunity with the Data Science team

1. Grants to visit Singapore and meet key partners working on the live project

2. Participation invites for UNDP flagship event in Singapore

*Additional prizes to be announced by the challenge partners


Build AI-powered apps with pre-trained models or create your own machine learning models

Azure AI puts artificial intelligence and machine learning at the fingertips of every developer. Want to build ML models? Choose between visual, automated, and code-first interfaces that simplify machine learning for any experience level.

Want to use pre-built models? Infuse computer vision, natural language processing, and decision-making capabilities into your apps with simple API calls.

The Azure Hackbook can be found here

Data Sets

UNDP dataset


Extended Submission period until May 19th

PHASE 1 | APRIL 17 – MAY 19

Phase 1 will consist of ideation (no prototype creation will be required during this phase). Participants will submit their solution design and architecture.

Solution design and architecture for participant’s chosen challenge(s) must be submitted by May 17, 2020. Judges will shortlist who moves onto Phase 2 based on Phase 1 ideation submissions.

Architecture slide deck, and Short video (2-4) minute explaining the approach. 

PHASE 2 | MAY 28 – JUNE 19

Participants who move onto Phase 2 will submit their prototypes for whichever challenge(s) they choose.

Prototypes must be submitted by June 19, 2020.

Virtual Session #1

Webinar : 15th April at 6PM SGT
Webinar Slideshow
Webinar Recording

Virtual Session #2

Korean webinar on 16th April 6PM Korea local time.
Webinar Recording(Korean)

Judging Criteria

Each submission will be scored in each round based on the following criteria with a minimum score of 0 and maximum score of 25 points.

With the final score being the average of the judges’ scores:

Feasibility of Solution (5 points)

Best Use of Azure APIs (5 points)

Solution Architecture with Azure (5 points)

Complexity to Implement (5 points)

Originality (5 points)


Armen Harutyunyan

Senior Advisor, Sustainable & Digital Agriculture, United Nations Development Program

Jagannadan Varadarajan

Head of Data Science, Grab

Victor Liang

Senior Data Science Manager, Grab

Suriyanarayanan Venkatesan

Lead Data Scientist, Grab

Ameya Mannikar

Senior Data Scientist, Grab

Ira Oliver Fernando

Data Scientist, Grab

Annie Mathew

Director, Developer Relations, APAC, Microsoft

Ian Choi

Developer Relations, Korea, APAC

Sudhir Rawat

Developer Product Marketing Manager, Microsoft


  • Teams of up to 5 participants are allowed. All team members must have completed the participation agreement to compete.
  • Participants of this hackathon must be 18 years or older and must be currently residing in Singapore, Korea, New Zealand, Thailand, Vietnam, Indonesia, the Philippines, Malaysia, Sri Lanka, Cambodia, Myanmar, Laos, Bangladesh, Maldives, Nepal, or Brunei. They need not be citizens or PRs.
  • You may not begin your project until the competition officially begins. 
  • Winning teams will be subject to a code-review at some point following the event or immediately before winning.


Who Can Participate?

Participants of this hackathon must be 18 years or older and must be currently residing in Singapore, Korea, New Zealand, Thailand, Vietnam, Indonesia, the Philippines, Malaysia, Sri Lanka, Cambodia, Myanmar, Laos, Bangladesh, Maldives, Nepal, or Brunei. They need not be citizens or PRs.

How are Teams Formed?

After signing up you will receive a link to the Microsoft Teams channel where you can chat with other participants and ask questions 

How will my project be judged?

Your project will be submitted and judged through Typeform

What is the Fresh Code Rule?

All code developed as part of the Microsoft Azure Virtual Hackathon must be fresh. Before the start of the Microsoft Azure Virtual Hackathon, developers can create wireframes, designs and user flows. They can also come with hardware. But to keep things fair, all code must be written onsite at the Microsoft Azure Virtual Hackathon. Other than that, almost anything goes and you can use any coding languages or open-source libraries

What are the Pre-Microsoft Azure Virtual Hackathon Virtual Sessions?

The Pre-Microsoft Azure Virtual Hackathon sessions are a virtual session hosted via Microsoft Teams. All developers, designers and entrepreneurs are invited to join the sessions. Microsoft, AngelHack, and challenge partners will go over the challenges, introduce the technology and answer any questions to help ensure an amazing experience.  This would also be a great opportunity for idea vetting

Who Owns the IP and Participation Agreement?


Participants own the rights to their projects they create at the Hackathon. Your team may create a prototype using data and/or API’s provided by The Sponsor and/or its Partner. This could mean that you or a teammate created the Technology, acquired ownership of the Technology from a third party, or may rely on binding written statements by the third party that owns or has the right to license the Technology indicating that you (or members of the public generally) are authorized to use that Technology in the manner you intend to use it. Your team will be disqualified if The Sponsor has any reason to believe that your team has violated the terms of this paragraph. You should consult with appropriate advisors or legal counsel if you have any doubt as to whether you are meeting the requirements of this paragraph. “Technology” means, without limitation, content (including pictorial, audio and audio-visual content), code, specifications, technical information, algorithms, images, design, art, music, graphics, SFX, data, and any other information or materials protected by any intellectual property right. Your team may bring to the Hackathon any pre-developed or licensed Technology that you plan to use in connection with your prototype, provided that such Technology meets the requirements of this paragraph.

By participating in the Hackathon, you will receive access to certain proprietary software, APIs, and/or other copyrighted materials, including pictorial, audio, video and/or audio-visual content owned by the Sponsor or its affiliates, partners or licensors