In the field of Project Data Analytics a lot of what is possible is unrecognised by the majority of the project community. We developed Project:Hack to show the art of the possible within a weekend. Our hackathons were created to provide a platform for professionals and students to get hands-on experience working with data on real business challenges.
Project:Hack10 is on the horizon and we're looking to optimise your experience by building your competitive appetite and preparing you for the upcoming event.
This talk will feature guest speakers from the top four winning teams at Project:Hack 9! They are from various organisations and sectors who will give insight into their past experiences of the event and how you can bring tangible benefits to your organisation.
- A run through of how challenges are developed in line with organisations and sponsors
- What to expect at your first Project:Hack and how to tackle it
- How to get started with Project:Hack10
- Case Studies of how challenges were tackled within teams over two days, which include:
1st place went to team 1a, a challenge set by Costain to extract construction pricing estimate data from an unstructured data source and transform this into a structured dataset, and secondly to create a visualised search tool that can be used to access the data in a quick and efficient manner.
2nd place went to challenge 10, developed by Projecting Success.
A challenge that involves using the power of a state-of-the-art natural language model (GPT-3) to automatically create tailored messages to different stakeholder groups on a construction project. This involved creating personalised messages to the various stakeholders using the data provided as prompts to GPT-3.
3rd Place went to Challenge 11a – A challenge that built on the work of the Knowledge Transfer Partnership (KTP) with the University of Nottingham. The challenge intended to improve cost forecasting and/modelling to make it an automated and efficient way to reduce cost. The challenge was to create a machine learning prediction model and further develop our dashboard to allow automatic access to the predictions.
4th place went to challenge 1b - This challenge was about making it easier to work with unstructured data to search and find information. The challenge required hackers to take a pdf filled with data and tables and pull that all into a completely new structure.
Kuldip Khella, Senior Estimator, Costain
Shailendar Palle, Senior Estimator, Costain
Jozef Quinn, Business Intelligence Analyst, Costain
Jon Barritt, Lead Principal Temporary Works Enigineer, Costain
Hamish Bryant, Reporting Analyst, Costain
Christine Curtis, Principal Process Engineer, Costain
Torben Schmidt-Hansen, Assistant Cost Intelligence Consultant, Mott MacDonald
James Fleming, Data Analyst, Projecting Success
Jack Reynolds, Data Analyst, Mace
Russell Willis, Data Liberator, Mace
Vipul Kumar, Geotechnical Engineer, Mott MacDonald and PhD student at University of Cambridge
James Garner, Senior Director, Gleeds
Jake Watson, Data Engineer, The Oakland Group