I was reading a Gartner research report, "How to Avoid Data Lake Failures" by Nick Heudecker and Adam Ronthal, and was struck by the similarities between the pitfalls they refer to regarding data lakes and how that translates into other technologies like artificial intelligence (AI).
Some of the highlights of their findings are, and I paraphrase:
- Data lakes are expected to be the "silver bullet" that will address all of an organization’s data issues
- Data lakes are implemented without specific goals in mind
- Data lakes have technical limitations that are often overlooked, misunderstood or ignored
This all translates really well if we replace “data lake” with “artificial intelligence” or even other new technologies. Let’s start by stating clearly, artificial intelligence is not a strategy. Any time we look at new technologies, we should always start with the question, “What do we want to accomplish?” We have met a lot of people who want to put all data into a data lake to create a “single source of truth” and then want to implement AI. Then they look for a problem to solve. We recommend turning that around and starting with a clearly defined purpose.
Another problem that we see regularly is the misconception that technology is all things to all people. For example, there is often the tendency within organizations to dump all data into data lakes to keep forever and then add AI on top to solve all problems. So let’s go back to the purpose. What is the project, the context, the rules, and let’s make sure we have clear objectives defined. Without that step, the problems have just migrated to new technology.
We hear a lot of talk in the industry around the terms “digital transformation” and “Pharma 4.0” which are, at their core, all about being transformative. However, some organizations are just looking to modernize or harmonize their data environments while continuing to run existing infrastructure which represents significant technical debt. Starting with an assessment which enables the opportunity to pause and look realistically at dimensions like the amount of technical debt, and the scope and speed of the transformation they are trying to accomplish is admirable. This is where companies like Aizon, who have spearheaded the use of artificial intelligence in regulated environments, can really help by bringing an outside perspective on where a company is and what the roadmap to get to where they want to go should include. We do this all with your need to adhere to compliance standards in mind. The benefits are compelling when we go through this kind of planning process.
If you’re interested in exploring how Aizon's AI Consulting Services can help you to jumpstart your technology journey or help you to define that roadmap, request a consultation.
By Lawrence Baisch, Chief Customer Success Officer for Aizon
Reference: How to Avoid Data Lake Failures by Nick Heudecker and Adam Ronthal, Gartner, refreshed 16 December 2019
