Casestudy: how Skullcandy used BI and analytics for product improvement
Skullcandy’s journey with advanced analytics started with the product development team daring to ask three big questions:
- What if we could predict return rates on new products before they were introduced?
- What if we could use insights around reviews and warranty claims to understand positive drivers, negative drivers, and sentiment to inform new product design decisions?
- What if we could use this data to focus our resources and deliver better products?
Those early days can be compared to a kid standing at the edge of a bowl at the skate park, getting ready to drop in for the first time. He knows it isn’t going to be pretty, but he has to start somewhere. Skullcandy knew their journey with predictive analytics and sentiment analysis was going to be a gradual progression that would eventually help to understand and better serve their customers.They knew they might end up with some bumps and bruises, but to gain the advantage they had to take that first leap of faith.
An open analytics platform would be the backbone of this next analytics frontier for Skullcandy. Here’s how they managed to answer the questions the Skullcandy product team dared to ask.
Predicting return rates on new products
The first piece of the puzzle was trying to see into the future, sod machine learning technology was used to help with the heavy lifting. They were most interested in exploring if it was possible to predict the return rate on a new product based on historical return rates of products with similar features.
If you lack a data science team, integrating machine learning technology with your open-platform BI tool is a powerful way to achieve the horsepower of data science while maintaining the ease of use that the average business user requires. A predictive analytics engine was fed information about historical warranty costs, claims, forecasts, historical product attributes, and attributes of the new products on the roadmap. Then the machine learning and predictive modeling engine tproduced the results.
Following a few false starts and some great iterative learning, a solid predictive data model of the warranty costs for future periods was created. That predictive output was then fed into the BI tool so it was possible to drill-down, explore, and use these predictions to make data-driven decisions, ask new questions, and understand cost drivers. For the product development team, these kinds of insights are a goldmine for exploring opportunities for impacting warranty costs on new products before they’re even released.
Using sentiment analytics to inform new product design decisions
With predictive data models telling what might happen in the future with your products, the next step was to use sentiment analysis models to tell what customers are saying and feeling right now. Again, with BI text and sentiment data could be integrated using a few different techniques. Some partners suggested using Python and it’s natural language processing libraries to understand what customers are talking about, and Amazon Comprehend to understand how customers feel about their products.
With this integrated data tech stack, it was possible to feed in text from customer reviews and warranty claims to be processed by a Python NLP Engine in order to pull out key themes. The same data could also be fed into Amazon Comprehend to measure the sentiment behind the themes, and which products were most associated with certain sentiments. Finally, this robust sentiment analysis was loaded back into the BI tool, turning what was previously a 'needle in a haystack' exercise into a richly engaging data experience yielding very targeted analysis for business users.
Where in the past Skullcany had to wade through disparate, siloed data, now they can correlate a stream of negative sentiment to reviews that mention a defect on the left side of a headset. And even take it a step further to put a dollar value on that negative sentiment, by connecting those negative reviews on a product to the same product’s warranty claims. Incoming products with similar design and engineering could be given extra attention by product designers and engineers before going to market. And visualization how a fix could impact the warranty claim forecast was easy. Full circle data experience: achieved.
If you’re considering a similar investment in your company’s data strategy, there are a few lessons learned along the way:
- Be open to false starts with data modeling. Like any other data project, it won’t be instantly clear what your data model should look like. And bringing the predictive models into the mix means you’re connecting data points from the past, the present, and the 'future' to build a model that provides actionable insights. It will be iterative. Be patient!
- Make the data easy to add to and modify. For the data team at Skullcandy, that meant using an easy to manipulate view in SQL as the main data source. This allowed the team to easily swap out code and change the view as they continued to build and iterate.
- You may not like what you see. It’s fun to explore the positive drivers and get lost in the positive reviews. One of the surprises that the NLP Engine identified in one product’s reviews was a predominance of the phrase 'for my son'. It was fun to think about why that might be.
But Skullcandy also came face-to-face with some harsh reviews. Not as fun to read, but when you invest in advanced analytics, sometimes that’s exactly what you came for. Your goal is to identify what isn’t working for your customers so that future products can deliver what they want and need.
At Skullcandy, they’re happy to report that 'dropping in' to the predictive and sentiment analytics game was worth the initial uncertainty. They answered some of their most pressing questions, came up with some new insights we hadn’t originally considered, and this project has helped concretely demonstrate to the company what’s possible with advanced analytics. As a result, they are further along on their journey as a data-driven company.