Bridg.it App: AI-Powered Collaboration for Sustainable Supply Chains

This document details the development of the Bridg.it app, an AI-driven platform designed to foster collaboration among businesses, individuals, investors, and SMEs to address sustainability challenges within their supply chains. The app utilizes machine learning methods, data analytics tools, and AI algorithms to identify and prioritize opportunities for collaboration, focusing on product life-cycle longevity and waste reduction management. It incorporates features such as a matching tool, recommender module, and business intelligence implementation using Power BI, supported by a compatible database like SQL. The app aims to benefit various industries by facilitating partnerships and continuously learning from user interactions to improve prediction accuracy. Challenges include competition from larger tech companies, rapid technological changes, and the need for extensive marketing to establish a customer base. The document includes app diagrams for login, registration, user account, and admin pages, along with references to relevant research and articles.

How will this App be built?
Machine Learning (ML) methods and data analytics tools will be used to provide data
useful data to a matching tool that will further provide inputs to a recommender module for the
users. Machine learning APIs like BigML, Google Prediction API, or Amazon Machine
Learning will be utilized in the App to add predictive features (Dorard, 2016). Power BI will be
implemented for business intelligence. Also, a compatible database like SQL is necessary due to
the numerous queries that will be happening instantaneously.
What will the App do?
This is an Artificial Intelligence (AI) based predictor that will enable businesses,
individuals, investors, and SMEs among others to positively collaborate in an effort to find
solutions to the most challenging sustainability problems that exist in their supply chains and in
particular the ones that relate to product life-cycle longevity and waste reduction management
(Smith, 2017).
The App will be trained through AI learning algorithms and draw from the rich repository
of industrial ecology research, case studies, and real-life problem-solving dilemmas. It will then
identify and prioritize the most promising opportunities for collaboration both within and across
the various industry supply chains (Zheng, 2015). The App will then use matching AI algorithms
to facilitate partnership connections that optimize on the opportunities identified. Through the

use of AI and machine learning, the App will continuously learn from the user interactions
becoming even more and more accurate in its future predictions.
What types of the industry will the App be of benefit?
The App stands to benefit most companies as collaboration has become an important
aspect of business today. For instance, Tech companies can collaborate with healthcare providers
to find solutions to unsolved medical problems (Klumpp, 2017). On the other hand, transport and
delivery companies may collaborate with other companies in the same niche to enhance their
delivery rates and efficiency while at the same time cutting on transportation costs through the
use of a share economy approach.
Scopes and any real business example
Retail companies such as Walmart collaborate with its suppliers to solve or enhance
productivity in their dealings. They have developed an inventory that notifies the suppliers about

the status of their inventories and when it’s optimal time to produce and deliver the next
shipment (Klumpp, 2017).
Transport companies such as Uber is already collaborating with food stores and
restaurants to deliver ready meals and food products orders to customers with high efficiency.
What kind of issues will be encountered with this App?
The App will encounter several challenges ranging from internal to external business factors.
Below are some of the problems that the App will face:
a) Serious competition from giant tech companies that have the funding and the resources to
implement the same model on a large-scale level (Murphy, 2018).
b) Technological factor - change is rapid, and the App will fight to keep up with the
changing technological trends.
c) Since the App is based on a start-up company, then funding and resources might be
scarce. Also, the App will have to do a lot of marketing for it to gain its customer base of
the market share.

App Diagrams
Login

Register

User account page

Admin page

References
Dorard, L. (2016, December 27). How to choose a machine learning API to build predictive
apps. Retrieved from Medium website: https://medium.com/louis-dorard/developer-
considerations-for-choosing-a-machine-learning-api-20e2de15eb3a (Accessed April 5, 2020)
Klumpp, M. (2017). Automation and artificial intelligence in business logistics systems: Human
reactions and collaboration requirements. International Journal of Logistics, 21. Retrieved from
https://doi.org/10.1080/13675567.2017.1384451 (Accessed April 5, 2020)
Murphy, A. (2018, December 13). Start-up challenges: The top 11 problems new companies
face. Retrieved from Teamwork.com website: https://blog.teamwork.com/11-challenges-
startups-face/ (Accessed April 5, 2020)
Smith, D. (2017, June 16). The growing impact of artificial intelligence on workplace
collaboration. Retrieved from CIO website: https://www.cio.com/article/3201001/the-growing-
impact-of-artificial-intelligence-on-workplace-collaboration.html (Accessed April 5, 2020)
Zheng, A. (2015, March 3). The 3 Key Steps to Building a Predictive App with Machine
Learning. Retrieved from Datanami website: https://www.datanami.com/2015/03/03/the-3-key-
steps-to-building-a-predictive-app-with-machine-learning/ (Accessed April 5, 2020)