It is no doubt a sign of progress that a significant proportion of organizations and managers today appear to feel guilty when they admit that they are making big management decisions in an intuitive rather than evidence-based way. Indeed, being data-driven has joined the ranks of “innovative”, “diverse”, and “socially responsible” as the one of most laudable features of organizational culture, at least if we go by company websites.
Although feeling the pressure to demonstrate that objective facts — instead of subjective preferences — underlie managers’ key choices is no doubt a major step towards actually becoming a data-driven organization, it’s an ambitious goal for any company, requiring a big cultural transformation, which will need to transcend the wishes of senior leaders to create real changes in how people think, feel, and act at all levels of the organization. And, as with any cultural transformation, managers are a critical agent of change. Here are three key talent management recommendations that should help your team to become more data-driven:
1. Foster critical thinking: While much of the current discussions around data focus on the role of technology and AI, it is really the human side of the equation that will remain the biggest differentiator for teams and organizations. As organization turbocharge their ability to gather more and more data — and it’s not so much about size, but rather about quality — what matters most is having people who can ask the right questions to the data. In fact, as Ajay Agrawal and colleagues argue in their recent book, artificial intelligence (AI) will allow for cheaper prediction, which explains why there’s so much demand for it. But human curiosity and critical thinking are needed to identify the main problems that AI and data can help to solve, and this process starts with you.
This means questioning your own biases, distrusting your intuition, and displaying a healthy degree of skepticism when presented with ideas and suggestions from others, in particular your team. Equally important, don’t reward others for coming up with intuitive ideas or ideas that feel intuitively right. Instead, celebrate critical thinking, curiosity, and the deeper desire to question things. For example, Amazon encourages disagreements to avoid groupthink and leverage the benefits of cognitive diversity.
Although people will differ in their general predisposition towards critical thinking, you can help them develop whatever potential they have if you put in place the right incentives, give people accurate feedback, and establish an informal and non-hierarchical learning culture where people can share views and ideas. For instance, at AirBnB, employees post problems into an internal knowledge repository that allows other people to provide answers or solutions. This simple attempt to crowdsource knowledge will elevate the problem-solving capabilities of your team by leveraging its collective intelligence.
2. Invest in training: Too often, there is a mismatch between the things managers and organizations say they value — e.g., innovation, soft skills, leadership talent, and data-driven decision making — and the resources they devote to enabling those things. The implications are obvious: if you want your team to embrace, or at least keep up with, the current data revolution, and approach work in a more evidence-based way, you will need to train them. This does not mean turning everyone into a data scientist, but leveraging the vast universe of virtual resources that exist within and outside of organizations. For example, many top universities — including the Ivy Leagues — offer free online courses on AI, data visualization, and data science, and leading corporations in this space, such as Google, offer a wide range of free resources and online courses on AI, analytics, and big data. So, the primary investment is not money, but time. And, of course, you need to incentivize people to make use of this time.
Meta-analytic studies suggest that well-designed training interventions can be expected to boost formal learning outcomes by .60 of a standard deviation — implying that the average individual in the training group will end up outperforming 73% of individuals in a no-training group. That said, individuals’ potential constrains how much they will benefit from a training intervention. Indeed, a comprehensive meta-analysis shows that for most jobs and work-related tasks, deliberate practice accounts for just 1% of the variability in performance, with the remaining 99% depending on individual qualities that were present (and measurable) before the training took place. In other words, most of the training-related gains in expertise or knowledge can be predicted by people’s initial potential, which makes good hiring more consequential than great training (see next point).
3. Hire the right people: When it comes to the training of quantitative, data-driven, or fact-based reasoning skills, there is well-established evidence for the competencies that predict individuals’ likelihood to learn and display these skills. First, this depends on their level of general intelligence or cognitive ability, which is the single best predictor of a person’s ability to solve well-defined reasoning problems and acquire formal knowledge in any area of competence. Think of it as a general measure of mental horsepower or cognitive processing speed. More specifically, individuals with higher quantitative or numerical ability levels (a subset of general intelligence) will find it much easier to pick up any training related to data analytics. Regardless of the expertise or knowledge base they already have, they will learn faster and better.
This may sound obvious, but the practical implication is that if you want your team to be quantitatively skilled, your best bet is to avoid hiring people with lower levels of numerical reasoning ability. And yet, there are also other psychological qualities determining whether individuals will learn to think more empirically and quantitatively: being high on Openness to Experience, curiosity and learnability will enhance people’s willingness to learn and think more rationally, as will their general level of motivation and conscientiousness. Thus, no matter how smart your learning intervention might be, and how well-designed and executed your program is, it will be more effective if the recipients are generally bright, curious, and hard-working — in fact, the profile of your team will be the biggest determinant of the success of your intervention.