Before integrating it in your first application, take a moment to familiarize yourself with the process of using the mltrons API to make forecasts and predictions.
We’ve worked hard to keep the high-level process simple.
Here’s the basic process:
1. Submit a dataset
2. Choose Target Variable
3. Run Auto-Model
4. Get Results
All Machine Learning processes must start with data and a question you are trying to gain insight into. This question could range from “How many shirt will I sell next Tuesday?” to “What will happen to my sales if these few variables change over the course of next few weeks?”
To use the mltrons API, you must provide us with a Dataset. This Dataset is simply a series of related values. For example, it could be number of shirt units sold each day for the last three years or the store sales data. It could contain attributes of many different products - the description of the product, color, type, year, date, transaction id, location, sales, customer id. Along with this historical data, you can add additional data points. This is where business intuition, understanding, and creativity come into play. These additional data points could be a series of calendar events such as Singles Day, a promotion running at that store that week, a major sporting event on TV that afternoon, or heavy snow over the lunch hour.
The data submitted is very important, as it is used to discover relationships within the data using a host of algorithms that are already present in the mltrons database. This discovery process happens during what we call ml-type and auto-model select.
A Auto-Model is simply the discovery process using the supplied Dataset.
There are several types of ML Algorithms you can initiate and each type of ML can help answer different types of questions, but all act on the datasets you provide.
Prediction is done when you want to make a prediction on data based on the discovered relationships in the data.
Forecasting is done when you want to forecast how some thing might change over time.
This is where the data science happens at scale. Behind the scenes, our auto-model select will work to discover what makes your Dataset tick, attempting to find what factors are influential to others, where the correlations are and ultimately provide what’s called a best mathematical Model. This Model is then used, and in many cases, stored permanently for you to reuse.
Once the auto-model select has completed successfully, the mltrons API builds a custom mathematical Model, based the data that was used to build, or train that model. You can think of a model as a custom algorithm built based on the relationships found between the different data contained in the dataset. Depending on the type of ML, the results will vary somewhat but generally will solve for a variable you want to predict, also called the target. Once the model is built, it can be evaluated and then used for predictions and forecasts. You can get a graph or download the results in a csv format to perform further analysis.