For those of you who don’t know me, my name is Stefani and I’m obsessed with data (and love Microsoft Excel). This interest is a far stretch from my political science degree, and an even further stretch from my original passion for journalism, but strangely, I find the same underlying beauty and potential in raw data that I find in international human rights studies. When made available, data is a global commodity, when gathered correctly it’s honest, and when analyzed appropriately, it sheds light on our strengths, weaknesses and potential solutions. Whether you have a corporate sales program that you need to see a profit turned by fourth quarter, or you are looking to end world hunger by analyzing statistics on food waste, a potential solution is hidden somewhere in the numbers (even if there are some corporate obstacles that you have to jump through to make that solution viable on either endeavor).
What is Predictive Analytics?
Predictive Analytics is the use of raw data, statistics and analysis techniques to form decisions for the future. Raw data is used to form the foundation of different models that can be wielded in different ways to form an understanding and inspire decision making (predictive models, descriptive models and decision models). While it seems complex, at its most basic execution, it’s quite simple. For example, your team is working on an inventory refresh for your corporate marketing products and there is one product that has caused some issues. You found a sharp increase in sales in January for this product, but it panned out for the rest of the quarter, flat lined in Summer, and bulked again in the Winter. This has led to mistakes in restocking, waste, and then a backlash of back ordering due to the unforeseen seasonal uptick. With machine learning and high-level inventory analysis, you can come closer to understanding exactly what needs to be ordered and when, ultimately decreasing waste and increasing sales efficiency.
While you’re here, I thought I might bring the world hunger issue back to the table. Predictive analytics can become much more complex in the international sphere and the potential solutions much more beautiful. We can take a look at visual analytics to see the depth of the food deficit color-imposed on a world map, compare that to the data of food waste, and quickly see that there is a major problem. Through analytics and algorithms, we can form an understanding of what this might mean for the future and what solutions might be lingering under the stark contrast. This global level of data analytics spirals into a need for understanding why corporations make decisions and how they make decisions to form a model for global change. This is not easy. It is actually extremely difficult, probably closer to impossible. However, with clear and honest data, this tremendous task could have some viable solutions.
How to Use Predictive Analytics to Decrease Inventory Waste (and Maybe Save the World)
Do you see the beauty yet? It’s amazing to talk about what data can do (small and big), but there are real solutions available to you whether you’re looking to accurately maintain inventory levels or if you’re looking to save the world. Big data is like a great big interactive art piece that you are inherently a huge part of (you are living and breathing data), and all of us have an endless number of tools to analyze data in our own way to make a difference (even if it is just a brush stroke).
I am proud to be a part of a company that offers one of these tools. The Recon GRP is introducing a machine learning inventory analytics module that will work to help companies cut down on waste and limit inefficiencies. By assessing inventory and sales level data, algorithms will automatically do the heavy lifting and suggest when to re-order inventory or highlight inventory that isn’t moving. This helps limit overprinting and overproduction when the need or want simply isn’t there for the purchasing audience. Working in a print and apparel industry, I have witnessed the immense amount of waste that only increases our environmental footprint (and the slow seep of profits). The value in this tool will not only be to help companies maintain profits, but decrease waste and environmental impact of overproduction.
Hopefully, you’re still here, so, back to world hunger (well, at least helping reduce local hunger). Inventory management is difficult, and with all the predictive analytics in the world, programs can be hit with a black swan event that can lead to a lot of food waste. When it comes to food, viable solutions for that waste are few and far between. The solutions available are generally extremely difficult, and usually the most efficient solution is to bag it and toss it. There is an additional solution that could help the food industry pinpoint inefficiencies and make use of food surplus that either happens consistently or sporadically (while quickly accruing tax deductions). MealConnect is an app that was created by Feeding America to provide safe solutions for getting surplus food to those in need in your local community. If you are in the restaurant, entertainment, grocery or any food related industry, please take some time to check out this app.
Data is beautiful. It is a medium that can be used to do so much across so many different modalities. Production based companies and endeavors can work to limit waste, limit their footprint and increase their profit potential. Food industries can use sporadic waste to feed the hungry while increasing their tax deductions. Understanding and using predictive analytics is a win-win (and it might save the world).