I have always wanted to specialize into a field and become an expert. But I have always been drawn into new areas where I could see a need for focus to create value in the projects I have been involved with. Now I have decided to own it and instead go for the opposite. To the degree that it informed the name for my personal blog. This blog is about my personal journey towards growing into an archetype role that I refer to as a “Full Spectrum Data Scientist”. It is the professional path that I have decided to travel.
I chose this blog name be able to encompass writing about the more human aspects of work and life. This includes handling stress, work-life balance task, time and energy management, maintaining work relationships and how to have fun and enjoy life. Sometimes I forget this, so I hope writing about it here can help me to focus on it more and maybe it could help others as well.
A full spectrum data scientist is a term I might have coined - at least I did not hear it used before. It is similar to “Full Stack Data Scientist” but it has a broader and more multidisciplinary connotation. An individual who is very broad and have experience in all areas related to data science needed to create value with solutions. This is including the skills of the more traditional data scientist skills like: data engineering, data analysis, and machine learning, MLOps etc. but a full spectrum data scientist sometimes also needs to learn cloud app development, cloud architecture, business intelligence dashboard building and even business development. Is very practical holistic focus, concerned with solving problems and to creating value.
Some will say cynically:
Jack of all trades, master of none.
Fair, - but I do not see that as a problem.
To create value often, you do not need to be a specialist anymore. You can be a generalist and just use ready made solutions where all of the complexity is hidden for you. Full spectrum data scientists take cheap shortcuts, and if suitable will choose the easiest “good enough” route. Just start with using a pretrained model, an API or a SAAS applications to do ML and solve business problem. Importantly, I still think it is crucial to “Think like a data scientist”, and using the data science process should be second nature to them. For instance, thinking evaluation methods and feedback loops in early and makings sure models is registered and governed with all the best practices.
But what makes a full spectrum data scientist different from traditional data scientist, is that they actually think more like designers. Designers spend much time on understanding the problem, the users and the context of the problem. They reframe problems so they are easier to work with, or getting to the root of the problem. They utilize proven tools in the “design thinking” toolbox in their work.
Thinking like a designer (or a start up company) with a bias towards action, and quickly getting something out to learn more about the problem and solution and get interacts with the end users.
In other words, most important assets are actually their soft skills like:
Great Communicators: These individuals are not only proficient in technical tasks, but are also skilled communicators, they can explain the results of their work to the people in the business who need to understand it. They can do this because they are possessing a vast arsenal of skills and knowledge that can be applied to many different problems.
Generalists: They are generalists, not specialists. They can see the big picture and understand how all the pieces fit together.
Value Creators: The are extremely focused upon the value creation. They are able to identify the most valuable problems to solve and then solve them in the most efficient way possible.
People Oriented: They are people oriented, they understand that the most important part of any project is the people involved in it. They know how to motivate and inspire others to do their best work.
Creative: They are creative, come up with new ideas and solutions that no one else has thought of before. They are able to think outside the box and find innovative solutions to problems.
Fast: They can quickly iterate on ideas and solutions, they will quickly prototype and test new ideas. They thereby quickly identify the most valuable problems to solve and then solve them in the most efficient way possible.
Pragmatic: They are pragmatic, they know that there is no such thing as a perfect solution. They understand that sometimes you have to make compromises in order to get things done. They embrace the “good enough for now” mindset.
Learners: They quickly learn to enough to get the job done, and then they move on to the next most value creating task.
This blog serves as a stepping stone for me to becoming a full spectrum data scientist. It is designed to be a repository of articles, tutorials, and videos that will equip me (and you!) with the necessary skills to thrive as a full spectrum data scientist.
While building a convincing AI demonstration can be deceptively easy, creating real value from a functional AI application is quite challenging.
I want to use writing in this blog to become great at bridging this gap.
I’m a senior data scientist with extensive experience in designing, developing, and operationalizing AI applications. My vision is to establish tools and processes that me and my colleagues can follow to allow full spectrum data scientists to swiftly develop and operationalize sustainable AI solutions to address business challenges.
By leveraging the best tools for the job, and always doing the minimum of what is required to get the learnings we need in a creative way, I believe it’s possible to greatly accelerate value generation.
As I evolve and grow in this journey, so will the content of this blog. I will share my learnings in the projects I do at work. Hope it will create value for you the reader as well.