In this post, we’ll cover the major design decisions involved in creating AHS2 and explain how each of the shortcomings we sought to overcome shaped the finished product. The Data Science team works closely with our product, customer success, and sales teams; we work to make sure teams are asking the right questions and then find those answers. As a Data Scientist at Asana, you’ll help them ask the right questions and answer them rigorously. We’re building new alerts around the AHS2, equipping CS with what they need to successfully reach out to unhealthy accounts. At the beginning of every sprint we go through the top goals, priorities, and accomplishments of each data scientist. They regularly provided us with qualitative indicators of account health that they’d learned from their time interacting directly with customers, and we would look for a way to quantify them given the available data.Seeing how much of a difference these new inputs could make on the performance of the model, we also worked to create a flexible system of model configurations that could easily train a new model with additional inputs. This both has an intuitive real world meaning and is mathematically quite useful, in that it can be used in any of the numerous calculations that ask for a probability, including computing things like the expected value of revenue lost to churn.We initially considered using a logistic regression or some other classifier that would output a probability by default. When I asked for help, one of the first pieces of advice I got was to ask questions, and boy, has that advice paid off.Whether it was in the form of attending user research sessions, participating in a random 1:1 meeting at work, or responding to a conflicting viewpoint, curiosity has always helped me despite my fears. Go a stage further, and instead of using email, messaging or Zoom calls to let people know you've completed a task or need their approval, you just update your status in Asana or similar work management tool.In the midst of this turmoil, many are discovering that when they digitize teamwork to this extent, they discover there are hidden benefits. And they can also see how their work ladders to something greater.Now that Goals is in place, the next step is to use all of this instrumentation of work processes to help people and businesses understand how they can work more effectively. With every data scientist working with a different team, and bringing their unique perspectives and skill sets to the table, there are so many avenues from which this complex topic can be explored. Because we gathered from our conversations that at least one to two months’ notice would be ideal for preventing an account from churning, we would label accounts as “churned” eight weeks out from their historical churn date. Headquartered in San Francisco with offices in New York, Dublin, Sydney, Vancouver, and Reykjavík, Asana is always looking for curious, collaborative people to be a part of their inclusive culture and help them achieve their mission.Their goal is to ensure that Asana upholds an inclusive environment where all people feel that they are equally respected and valued, whether they are applying for an open position or working at the company. This involves working closely with The synergy between these three roles is one of the more interesting aspects of my role. To make sure the AHS2 would meet their needs, we discussed their workflow and process of reaching out to users.