The four forecasting feats of the Evo algorithm for retail

Let’s be honest. The retail forecasting models of ten years ago won’t get the job done today. Modern technology, AI and machine learning are now light years ahead of the old forecasting models, bringing unheard of accuracy to those that use them. Unfortunately, most retailers haven’t “gotten the memo” on this and are stuck in the past using obsolete forecasting systems to make decisions.

If you want success in today’s highly competitive retail market, you’ll need to utilize the benefits of big data and machine learning. The problem is that most retailers aren’t technically savvy enough to build these systems on their own. That’s where Evo comes in.

We give retailers the tools to analyze and understand their data, while making more accurate and less biased predictions that ever before. In this article, we will take a look at four specific ways Evo delivers better forecasting results to clients.

1. Price signals can be the needle in the haystack

Price signals are vital in retail -- they tell companies where demand is and what price level is best. But most retailers don’t have the modeling sophistication to identify the more subtle price signals that may be buried within high sales volatility. Missing these subtle indicators means that retailers will move slowly, bleeding cash while they wait for enough data to pile up so they can make any decisions or changes.

While previously extremely challenging, finding price signals in their earliest states, in high-sales-volatility environments, is one of Evo’s specialties. Our software can identify price signals as small as 5% average change, even when sales volatility is 30% or higher.

We achieve such sensitive analysis by using our proprietary library of machine learning models to analyze the data from many different angles and getting a bigger and fuller picture. These models range from the ordinary pre- vs post-performance comparison, to our black box forecasting algorithms that compare real performance to a baseline hypothetical of no price changes. As a result of studying these multiple data streams, particularly stock outs and changes to product life cycle, we are even able to tell if variations in sales are due to price changes or some other factor.

The ultimate result is real time business intelligence that gives retailers the agility to avoid losses and capture higher profits. Those small signals, the needles in the haystack of all of your data, are waiting to be found with our Evo data tools.

2. Analyzing promotions in real-time

A/B tests, the retail standard for measuring the impact of promotions, are slow and expensive in terms of work, risk and time. However, with the advent of big data and machine learning, this standard has passed its sell-by date. Say goodbye to guesswork and goodbye to failed test promotions.

Our software automatically measures the impact of promotions (in real-time) without A/B testing. With Evo, retailers will know right away when it’s time to nip an ineffective promotion in the bud or expand a profitable one.

More importantly, Evo helps forecast which promotions will work out in the first place! By measuring the results of historical promotions and other relevant data, we can simulate the behavior of new promotions before they’re even launched.

3. Accurately forecasts for new-product performance

New products contribute around one-third of sales for the average retailer and up to 70% for industries like fashion and gaming. These figures are set to rise as product life cycles get shorter and retailers continue to increase product assortment.

So the stakes in forecasting new-product performance are extremely high. If new-product forecasts are too low, retailers face a huge loss in sales; if they are too high, on the other hand, retailers are stuck holding a significant amount of unsellable inventory.

Traditionally, retailers used price and sales volumes to forecast future product performance. They predict price elasticity and future demand using simple static models based on what happened last year.

The problem with this sort of analysis is that it takes very little data into account. Evo solves this problem by utilizing machine learning algorithms to back-test the impact of a large number of factors on sales volumes.

Evo’s analysis includes elements like seasonality, weather, traffic, competition, promotional intensity and brand loyalty, to name a few. In fact, such machine learning algorithms can incorporate up to 200 discrete factors!

The result is a much-improved estimation of future sales at various price points. Moreover, Evo’s black box algorithms work in real time, making dynamic pricing recommendations as any of these influential factors change.

4. Estimating the probability of sales despite low volume

Just like with pre-launch products, it’s difficult to decide how to allocate inventory and set prices with newly introduced products. Sales volumes tend to be low for products just introduced to the market, which makes forecasting challenging.

Harder still is forecasting at the micro-level of individual stores. Stock-outs occur at the store-level and pricing varies among stores, so it is necessary to forecast the probability of sales and expected sales volumes at the store level.

Again, relying solely on past sales data won’t work in this situation. That’s why Evo employs a much wider set of factors beyond price and sales volume to predict product performance. This allows us to estimate the probability of sales at the item, size or store level, even when sales volumes are tiny.

An unbiased opinion is key!

Businesses tend to be optimistic about new products. This positive outlook often leads to inflated sales forecasts, especially when there aren’t many data points to go on.

Evo’s technology removes this negative influence of human bias. Because we have enough data to make accurate predictions, we are able to go by the numbers and leave out biased opinions. Our algorithms don’t change whether we like a product or not. This means that retailers get an honest evaluation that leads to better results.

One of our greatest value propositions is the ability to give retailers better information in real time. Let us crunch the numbers and we’ll keep you a few steps ahead of the pack.