Subscribe. Scale. Succeed.
We’re so confident you’ll love Akkio, we’ve made our service month to month. Ideal for people with commitment issues and ROI desires.
Forecasting is one of the most common use cases for machine learning. It allows you to predict your future revenue, what your costs will be, or even commodity prices.
Forecasting is also difficult. Traditional methods require time-consuming manual work, data engineering, and a high degree of statistical expertise. Akkio makes forecasting easy and affordable, even for non-technical teams.
Below, we’ll explore the process of building and deploying a commodity-price forecasting model from a dataset of avocado prices. Commodity prices have significant impacts on global economic activity, and are an important source of export earnings for developing countries, in particular. Commodity price forecasts are thus crucial for economic policy planning.
Commodity price instability leads to increased poverty, and in the worst cases, is devastating for hundreds of millions of people suffering from food insecurity, bringing about marked increases in starvation and child mortality. As MIT writes, volatile commodity prices also contribute to disastrous financial crises.
In short, forecasting commodity prices is an incredibly important use-case, with forecasts impacting billions of lives. These forecasts are also useful for everyday professionals involved with commodities, such as investors and commodity managers.
To get started, sign up to Akkio for free. As with any machine learning task, the first step is getting historical data and picking a column to predict.
In our video tutorial, the historical data is an avocado prices dataset, originally sourced from the Hass Avocado Board. The dataset features historical data on avocado prices and sales volume in multiple areas of the United States.
Our target column is called “average_price,” and we can use machine learning to forecast the average price.
This dataset is already uploaded to Akkio for demonstration purposes, which you can see on the homepage as “Forecasting Demo,” but you can upload any dataset you want by simply clicking “Upload Dataset.”
Below, we’ll explore how to build and deploy a forecasting model. First, hit “Create New Flow” on the homepage, and you’ll see the interface below.
Then, click “Table” to upload the avocado price dataset. When that’s uploaded, you’ll see an overview of the dataset, including the number of rows, the data types of each column, the latest upload date, and a scrollable preview of the dataset.
Now, we can click on the second step in the AI flow, which is “Predict.” Under “predict fields” you can select the column to predict, named “average_price.”
Then just hit “Create Predictive Model,” and you’re done! In the forecasting demo, the model has already been made, but it takes as little as 10 seconds to train a model from scratch. You can also select a longer training time—from 1 to 5 minutes—for potentially more accurate models. Keep in mind that longer training times aren’t always better, and may lead to overfitting.
Also note that you don’t need to pay for model training time, unlike with many typical automated machine learning tools, so feel free to build as many models as you’d like.
After a model is created, you get a simple overview, which highlights the top fields, model prediction quality, sample predictions, and more. There’s also the option to “See Model Report,” which lets us easily collaborate with others and share these model details with anyone, even if they don’t have an Akkio account.
In short, we’ve discovered that it’s very easy to build a highly accurate forecasting model.
Now that we’ve built a model, it’s time to deploy it in the real-world.
With Akkio, it becomes trivial to deploy complex machine learning models. The forecasting demo shows deployment via API as the third step, which is a powerful way to instantly serve predictions in any setting. It’s also possible to deploy through Salesforce, Zapier, or web app, with many more methods coming soon.
Simply click “Add Step” and your preferred deployment method. To deploy via web app, for instance, click “Web App” and then “Deploy,” and you’ll have a live link you can share with anyone to make predictions on new data.
That deployed web app will look like the below, with input fields for users to enter new data, and a “Predict Fields” button to send the data to Akkio and get a prediction back. Users can also upload a file, such as an Excel sheet, a CSV, or JSON.
Going beyond a web app, you could deploy the model in practically any setting with Zapier, a no-code automation tool that connects tools with “Zaps.” Zapier allows you to link up thousands of different tools, so no matter where your data is coming from, it’s easy to connect it to Akkio to get a prediction.
If you’re looking for more technical power, you can also use Akkio’s API, which is formatted as a Curl command, allowing you to send a GET request that contains your flow key, API key, and input data, and get a prediction back.
You can replicate the steps we’ve taken to forecast any metric, such as revenue, demand, or even the spread of a pandemic.
As long as you have the historical data, you can connect it with Akkio, select a column to forecast, and deploy through a variety of methods.
At Akkio, we believe that AI is the future. And when it comes to the future, forecasting plays a critical role in how businesses set their strategy and course of action.
Using Akkio’s no-code AI, you can effortlessly build forecasting models from any data, and deploy in any setting.