GeViz

Team

Proposal

Poster

Application

Research Paper

PROBLEM & MOTIVATION

GeBIZ is a Singapore Government’s one-stop e-procurement portal which facilitates tender activities between Singapore government and local and overseas suppliers. Currently, there is no available tool to aid the public and ministries to understand and gain insights on the procurement made by the government under each ministry. Hence, we are motivated to create an interactive visualisation tool on government's procurement spending to allow the public and ministries to identify spending patterns and gain insights into procurement spending under each ministry.

OBJECTIVES

In this project, we are creating a visualisation that is able to show the following:

• Gain an overview of procurement spending made by each ministry and agency
• Identify the relationships between ministries, agencies and suppliers
• Identify what are the goods and services procured by ministries and agencies under each category

SELECTED DATASETS

The following datasets will be used for analysis , as elaborated below:

Dataset/Source	Data Attributes	Rationale of Usage
Government Procurement Data (https://data.gov.sg/dataset/government-procurement)	Tender No Agency Tender Description Award Date Tender Detail Status Supplier Name Awarded Amount	To gain information on government procurement such as tender description, amount and supplier information
Ministry and Agencies List	Ministry Agency	We will be looking through the Singapore Government Directory (https://www.gov.sg/sgdi/ministries) to categorise the agencies into their respective ministries. This will allow us to visualise the procurement spending on a ministry level.

APPROACH

Exploratory Data Analytics
We used Tableau to perform EDA to better understand our dataset and to aid us in the conceptualization of our story board.

Data Cleaning and Feature Creation
We used Excel and Python to create a new column showing the Ministry that each agency belongs to by merging with data obtained from the Singapore Government Directory.

Text Classification using Support Vector Classifier (SVC)
One of the key challenges of working with the provided procurement dataset is the absence of categorization of each procurement transaction. Instead of labelling manually, we applied machine learning to classify the tender descriptions into different categories. We firstly scraped the procurement descriptions and categories from GeBiz website using Selenium and BeautifulSoup libraries in Python to be used as the training and validation dataset in our Support Vector Classifier model. We were able to achieve 90% for training accuracy before performing the categorization prediction.

Government Procurement Dataset after Text Classification

Dataset/Source	Data Attributes
Government Procurement Data	Tender No Agency Tender Description Award Date Tender Detail Status Supplier Name Awarded Amount Category Sub Category

Visualization in R
The web application will be built in R and deployed to Shinyapps.io

BACKGROUND SURVEY OF RELATED WORKS

Some of these visualizations that we draw inspiration from, are as follows:

Reference of Other Interactive Visualization	What We Can Learn
Title : Pareto Analysis of Suppliers Source: https://goo.gl/P9RjHk	The use of pareto chart allows us to identify the component(s) which is/are contributing significantly and how the categorises value sums up cumlatively.
Title : Word Cloud on Procurement Details Source: https://linpack-for-tableau.com/data-visualizations/tableau-dashboards/procurement-dashboard/procurement-cockpit/	Based on the size of the words, we can identify the keywords quickly. We can learn that by making frequency used keywords stand out can prevent us from overlooking it if it is presented in a tabular format.
Title : Breakdown on UK Government Spending Source: http://www.nickmalleson.co.uk/2014/02/uk-government-spending-treemap.html	Based on the chart, we can gain an overview of how the spending is breakdown according to the size and colour of the box. From this, we are able to identify outliers or signficant contribution quickly at a glance.
Title : Team Budget Breadown Source:https://acquireprocure.com/spend-analysis-visualisation/3-reasons-procurement-professionals-use-sankey-diagrams	Based on the path of the sankey chart, we are able to identify the cash flow from one end to the other end. The size of the path allows us to to identify how signficant it is in terms of value.
Title : Analyzing Involved Authorities, Tenders and Companies Source: https://linkurio.us/blog/exploring-e1-3-trillion-in-public-contracts-with-graph-visualization/#!prettyPhotooard	Based on the charts, we are able to identify key relationship between objects quickly based on the nodes and edges. From this, we can find common nodes as well.

BRAINSTORMING SESSIONS

During our brainstorming session, we came out a list of visualization which are able to achieve our objectives and eventually shortlisted 4 visualization - Tree map, Network Graph, Sankey Graph and Word Cloud. After rounds of refinement and consultations with our Professor, the image above is the final draft for our visualization.

PROPOSED STORYBOARD

Our group has proposed the following storyboard in the use of our visual application:

Proposed Layout	What We Can Analyse
Overview of Procurement Spending Source:https://www.r-graph-gallery.com/treemap/	Treemap to show the spending breakdown for each category of all agencies under the selected ministry. The interactive filters are year and ministry.
Relationship between Ministry and Suppliers Source: https://cran.r-project.org/web/packages/visNetwork/vignettes/Introduction-to-visNetwork.html	Network diagram to show the relationship of agencies and suppliers of the selected ministry. The interactive filters are year, ministry and range filter which allows the user to filter the suppliers based on the procurement amount.
Cashflow from Agency to Suppliers Source: https://www.r-graph-gallery.com/sankey-diagram/	Sankey diagram to show the cash flow between selected agency and suppliers for the selected category. The interactive filters are year, ministry, agency and category.
Word Cloud on Goods and Services Procured Source:http://www.sthda.com/english/wiki/text-mining-and-word-cloud-fundamentals-in-r-5-simple-steps-you-should-know	Word cloud to show an overview of the tender description for the selected agency and selected category. The filters are year, ministry, agency and category. We added a searchable table below the word cloud to allow the user to search for keywords and view the exact tender description

TOOLS & TECHNOLOGIES

Tools and technologies

Data Architecture

KEY CHALLENGES

The following are some of the key technical challenges that we may face throughout the course of the project:

Key Challenges	Mitigation Plan
Unfamiliarity with R and Rshiny Libraries	Attend R Shiny Workshop Independent learning via online resources such as Datacamp Ask team mates for help
Unfamiliarity with Libraries for Machine Learning and Web Crawling	Clean, transform and analyse data together Independent learning via online resources
Data Cleaning and Transformation	Need to crawl data on website to obtain training data for text classification Clean, transform the data together

TIMELINE

REFERENCES

• https://www.dsta.gov.sg/docs/default-source/dsta-about/dh02200602-gebiz-from-vision-to-reality.pdf?sfvrsn=2
• https://support.rstudio.com/hc/en-us/articles/201057987-Quick-list-of-useful-R-packages
• http://enhancedatascience.com/2017/07/06/pick-best-r-packages-interactive-plot-visualisation-22/
• http://www.sthda.com/english/wiki/text-mining-and-word-cloud-fundamentals-in-r-5-simple-steps-you-should-know
• https://www.r-graph-gallery.com/
• https://rpubs.com/brandonkopp/creating-a-treemap-in-r
• https://cran.r-project.org/web/packages/visNetwork/vignettes/Introduction-to-visNetwork.html
• https://www.displayr.com/sankey-diagrams-r/
• https://towardsdatascience.com/using-networkd3-in-r-to-create-simple-and-clear-sankey-diagrams-48f8ba8a4ace
• Datacamp Building Web Applications in R with Shiny Course
• https://www.r-graph-gallery.com/the-wordcloud2-library/
• https://rstudio.github.io/shinythemes/
• https://rstudio.github.io/DT/shiny.html
• https://rstudio-pubs-static.s3.amazonaws.com/72023_670962b57f444c04999fd1a0a393e113.html

COMMENTS

Feel free to leave us some comments so that we can improve!

No.	Name	Date	Comments
1.	Insert your name here	Insert date here	Insert comment here
2.	Insert your name here	Insert date here	Insert comment here
3.	Insert your name here	Insert date here	Insert comment here