Start Data Science in Parallel with other Initiatives

Data science should not be delayed until after data governance and other supporting initiatives are implemented. While this will require additional effort from stakeholders, the costs are outweighed by the increase in data-driven thought, organizational familiarity with data science workflows, and impact on the bottom line.

Source: Author via Inlet Labs


Enterprises undertaking data-driven transformations often begin from a point of low data maturity. Effectively implementing data science projects in these environments is difficult due to characteristics such as siloed data, poor data documentation, and unfamiliarity with data initiatives. Tackling these issues require a long-term strategy with initiatives for data governance, data management, and…


Data science and machine learning present new opportunities for improving public spaces. Leveraging these technologies for smart cities can make our communities more livable, more sustainable, and benefit local economies. They can assist with understanding key questions in city planning and urban design such as how public spaces are used, how many users there are, and who the users are.

In this post, we’ll look at a proof-of-concept system we implemented to answer these questions using machine learning for video analysis. It’s an approach that’s easy to deploy and cost-effective. We’ll focus on street intersections in particular, where design…

Water is a critical resource in the Pacific Northwest. The effects of climate change on hydrological resources will be felt by a wide range of communities. Cities, First Nations, farmers, and the environment will all be affected. Effective management of water resources will become increasingly important to meet the diverse needs of the region.

Climate models provide insight into how hydrological conditions and water resources will change in the future. This includes changes in the availability of water, and the occurence of catastrophic events like floods and droughts. Understanding these changes is essential to prepare and adapt for the future…

Neural networks generate a lot of interest. However, it’s not always clear to people outside of the machine learning community the problems they’re suited for, what they are, or how they’re built. We’ll address these topics in this blog post, aiming to make neural networks accessible to all readers. For those with programming experience, I’ve appended a Jupyter Notebook at the end which you can follow to build your own neural network.

Most commercially successful applications of neural networks are in the area of supervised learning. In supervised learning, we are trying to build a model that maps inputs to…

Conrad Koziol

Data Science, Machine Learning, and Earth Sciences. Principal at Inlet Labs.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store