UK: The Transpennine Route Upgrade programme is using data-driven forecasting and risk management software from nPlan to reduce the optimism, recency and salience biases in its project schedule forecasts.
The software looks at past project schedules and uses a deep learning technique to build a model of how the customer executes projects and then capture how activities play out in different contexts.
Once the model has been trained, it can be fed schedules for upcoming projects, enabling it to generate a forecast of how the project would play out, along with detailed information about the risk profile of every activity.
This enables users to focus on the riskiest elements of each project and test the impact of various risk mitigation scenarios.
‘The Transpennine Route Upgrade is an ambitious and complex multi-year programme’, explained Richard Palczynski, Head of Strategic Programme Controls at TRU. ‘With nPlan as a delivery partner, we’re able to take a new approach to analysing our schedules — removing the human bias in favour of learning from actual data and historical performance — and driving efficiency into the process. Being able to get more frequent analysis done on a larger volume of schedules is a game-changer for us.’
