EasyBiz

Project Info

Team Name


ARVIS


Team Members


Jack and 1 other member with an unpublished profile.

Project Description


There are two types of end users will use our solution, the business owner can use our mobile app to find the place to start a new business or grow the existing business. The government can access to the web portal to see the where are the least business growth places in the country, the AI will provide with city improvement suggestions that will attract more business to come and help the existing business to grow.

We have developed a simple machine learning model and a judging AI algorithm to find a best business location. For example, you want to open a café shop in CBD area, and your budget is 100k,
Our AI will look for your business competitors around that area, your potential business streets should be a little bit further away from the existing competitors, you don’t want to open a café just besides another café shop. Then a few streets that have the café business capability are found. Then pedestrian volume and car park bays are the factors to be considered to analysis these streets, the AI will select a list of locations to the user based on the pedestrian volume and number of available car park bays from high to low.

The future development of this solution would be adding more relevant data sets to the machine learning, more data learning model should be added and unsupervised machine learning could also be conducted in order to achieve more accurate place finding. The business owner may receive notifications that a few new places are available for business growing based on the latest government development plan. The government could receive notifications that infrastructural facilities in a certain area needs to be improved such as car park space, public transports.


Data Story


The solution utilises the latest Google Machine learning to analysis a few data sets such as Cafes and restaurants data, City of Melbourne population forecast, prdestrain volume, bar and pubs, on-street parking bays. We developed some supervised machine learning data models for the machine learning to extract the patterns and criteria that our application needs. The decision is made by AI based on the requirement from the user and the machine learning data.


Evidence of Work

Video

Team DataSets

On-street Parking Bays

Description of Use This data is a source for machine learning and an AI judging criteria to help business owner to find a better place to start a business.

Data Set

Cafes and restaurants, with seating capacity

Description of Use This data is a source for machine learning and an AI judging criteria to help business owner to find a better place to start a business.

Data Set

City of Melbourne Population Forecast

Description of Use This data is a source for machine learning and an AI judging criteria to help business owner to find a better place to start a business.

Data Set

Pedestrian volume

Description of Use The pedestrian volume data is a criteria to make the decision for the retail, hospitality business owners to open a business in a location.

Data Set

Bars and pubs, with patron capacity

Description of Use This hospitality business data is used as a judging criteria if the proposed location is suitable for a hospitality business to a similar bar or pub.

Data Set

Challenge Entries

A New Start

How can we improve the process of starting or growing a business?

Go to Challenge | 21 teams have entered this challenge.

Activate Melbourne - A Prosperous City

This challenge aims to simplify the steps taken to decide where a new business could be located, or where there is underutilised space in the city.

Go to Challenge | 10 teams have entered this challenge.

My Victoria: Supporting small business making big decisions

Where are the best places for certain business types to be based?

Go to Challenge | 12 teams have entered this challenge.

Innovation space - A City Planning for Growth

This challenge aims to showcase innovative new ways the city’s public space can be utilised and reimagined.

Go to Challenge | 8 teams have entered this challenge.