Intelligence. Beautifully engineered. We are a data science agency.

Nerve Analytics uses communication traffic to help companies forecast productivity and project performance, and understand how performance is impacted by the allocation of resources.

Nerve Analytics was first developed as a way to monitor and forecast team and R&D productivity in Formula One teams. The technology hinges on the use of statistical and machine-learning methods to discover structural relationships between the information flows within an organization and the productivity of its workers and their progress on projects.

In Formula One, the operational performance forecasts serve as an early-warning system regarding the efficacy of resource allocation strategies, which in turn can improve teams’ investment yield by allowing them to exit poor projects early and invest more heavily in likely successes. The approach realized an effective 12% increase in the R&D budget under consideration at one F1 team.

Read more →

We developed a more flexible, more robust method for valuing complex assets in complex, highly volatile environments that outperforms its benchmark by nearly 20%.

The client wanted to investigate the viability of extending real options methods to risk management settings that are generally not amenable to an options formulation. Armed with a data set of more than 200,000 decisions for the domain under study as well as data on the underlying asset movements, we combined machine learning methods with a simple options model to build an accurate forecaster of asset movements and an algorithm that improves allocation decisions by nearly 20%.

While real options are increasingly well-accepted as instruments to value and invest in R&D projects, their applicability remains limited for the restrictive assumptions they place on uncertainty and for their inability to accommodate many features of complex decisions, like multi-agent competition. We used a very large data set of asset movements in a complex setting to forecast asset prices accurately and to solve the problem of making optimal decisions on the back of these forecasts.

Read more →

Since 2009, QuantumBlack has provided software, analytics, and support to 3 of the top Formula One teams, helping them win more than 300 Championship points through better race strategy decision-making.

Formula One is a hyper-competitive sport. At the end of 2010, 10 of the top 20 drivers were separated by 5 points or less in the Championship; 7 by 2 points or less. The relative competitiveness of the field has in turn made race strategy a critical aspect of that competition.

We have developed a powerful suite of competitive analysis and statistical estimation techniques, opponent forecasting and strategy optimization methods, and advanced visual interfaces for race strategy decision-making. These algorithms have assisted in the accrual of more than 300 Championship points since 2009.

Read more →

Since 2010, Formula One teams’ operations are subject to a headcount and spending cap, making resource allocation and utilization an ever greater part of how teams compete in the development race. Working with one Formula One team, we developed a decision platform to help improve how resources are deployed to development and production activities.

How resources are deployed across development and production activities has implications for the rate of innovation and the speed at which a team derives benefit from these innovations. The constraints imposed on teams’ operations by the Formula One Teams’ Association (FOTA) Restricted Resource Agreement (RRA) have made it all the more critical for teams to understand the effectiveness of how resources are deployed across their organization.

Working with one Formula One team, we developed a decision platform to help capture data about resource utilization and performance gains, investigate and understand the tradeoffs of different resource allocation strategies, and help optimize resource deployments to maximize performance over a specified time horizon.

Read more →

Our client faced complex investment decisions due to the rapid evolution of software, electronics and materials – in stark contrast to their core products whose development and lifespan measured in decades. They were looking to improve the quality and efficiency of this high-value decision process that due to the trade-offs in timing, risk and investment was complex, slow and expensive.

To address this we deployed Carbon, our proprietary decision mapping technology designed to inform and adapt strategic decisions over time. Carbon enables decision makers to rapidly map out options, determine the optimal path based upon what is known today and recalibrate as real-world events unfold. We helped the client develop a business object framework, integrate with their internal data sources and provided training on the options methods used to their staff to embed the capability on an ongoing basis.

Read more →