o9 Digital Brain — Driver based Machine Learning
In this video, we will discuss how o9's digital brain can help you improve forecast accuracy and reduce the time spent in forecasting. We will start by discussing the importance of collecting sell-out data and other leading indicators. We will then discuss how o9's machine learning algorithms use this data to make better predictions. Finally, we will discuss how o9 highlights actionable exceptions for planners to make faster and more insightful decisions.
We will show you how o9's digital brain can help you:
- Improve forecast accuracy by up to 20%
- Reduce the time spent in forecasting by up to 50%
- Make better decisions with actionable insights
We will also show you how o9 can help you:
- Understand consumer behavior
- Identify market trends
- Plan for seasonal fluctuations
- Respond to unexpected events
We believe that o9's digital brain is the most powerful forecasting tool on the market. If you are looking to improve forecast accuracy and reduce the time spent in forecasting, then o9 is the solution for you.
With o9's digital brain, we can help you improve accuracy and reduce the time spent in forecasting. So how do we make this happen? It is through a combination of process and technology. Let's look at process first By collecting not just customer orders, but also Sell Out data.
Extra insights on consumer behaviour can be obtained. Notice that even though the customer Sell Out is stable, the ordering pattern is crazy. This bullwhip effect is causing continuous missed shipments and leading to low fill rates. We can share these insights with key customers and work collaboratively with them to understand and normalize the ordering patterns.
Now let's look at Agile planning. If we overlay weeks and months in a calendar, we can see that in a monthly planning frequency. The weekly signals are ignored. Changes in consumer behavior or changes in stocking levels are only visible after four or five weeks.
With o9, you can easily move from a monthly to a weekly planning drumbeat and then react faster to changes in the market. Now let's talk about technology. The o9 digital brain converts data into knowledge by connecting large amounts of discrete data using "nodes" and "edges". o9 Machine Learning uses this knowledge built on both lagging and leading indicators to make better predictions.
o9 also highlights actionable exceptions for planners to make faster and more insightful decisions. Let's look at some examples of o9's intelligent predictions and insight. This graph shows how sell out data has a fairly strong correlation with search trends for vitamins from Google. Consumers are obviously looking for the product in question, and here we can see that influenza surveillance data, which is termed ILI activity, is a strong leading indicator of sales and forecast of immunity booster products such as herbs.
This graph presents a sudden jump in sales in April. It also coincides with increased online search for an action figure. If we now overlay the action figure movie release, we see a remarkably strong match. Having visibility to these marketing activations and learning from them, will help us be ready when the sequel is released.
This image shows a huge spike in orders for the barbecue sauce product eight weeks prior to a holiday, o9 shows a clear link to holidays. Obtaining the holiday calendar in advance will certainly help prepare for demand surges and remove surprises. This leading indicator is even more important when the holidays are not fixed and changed from one year to the next. And now a graph showing how mobility data aligns with sales of boardgames.
The surge in demand for home based entertainment occurred during the COVID lockdown. Mobility driver data can be used to understand and cleanse these anomalies for planning future years. As you can see from these examples, the o9 digital brain with machine learning prediction can dramatically improve forecast accuracy, provide actionable insights and significantly reduce the time spent in the forecast consensus process.