Improving your business’ E-commerce Support with AI using MindsDB & MonkeyLearn

Cover Image for Improving your business’ E-commerce Support with AI using MindsDB & MonkeyLearn

Over the years we have seen the increase of companies’ dependence on their E-commerce to grow their business, which means that managing E-commerce support has become vital to ensuring that their business thrives in order to be successful.

Companies are met with challenges to streamline their ticket routing process and analyse the type of E-commerce support they need to provide to customers. MindsDB can solve these obstacles faced and simplify practices used for ticket routing and data analyses using text classification models. You will be able to provide multi-channel support to your customers,manage incidents

MindsDB’s integration with MonkeyLearn allows you to harness the power of MonkeyLearn’s No-code Text analyses features which you can utilise in improving your business. MindsDB allows you to use MonkeyLearn’s pre-built and custom models that gives you access to features,like text-classification, according to a user’s needs like business, reviews,surveys and support analyses.

In this blog we will explore:

  1. An example of how to classify E-commerce Support Tickets using MindsDB with MonkeyLearn

  2. What kind of application developers can build with MindsDB and the MonkeyLearn Integration

  3. Build a AI/ML model with MindsDB using MonkeyLearn

In this example, we will build a model that classifies E-commerce support tickets by providing tags to text using of MonkeyLearn’s pre-made model E-commerce Support Ticket Classifier.

This use case can be used to improve the ticket routing process to ensure that the E-commerce support tickets get routed to the relevant department that needs to resolve the tickets and improve productivity. It can also be used to analyse reports on the amount of different E-commerce Support tickets that have been received to have an overview on any issues or successes.

How to bring MonkeyLearn Models to MindsDB

Before creating a model, you will need to create the ML_ENGINE for MonkeyLearn using the CREATE ML_ENGINE syntax

Create ML_ENGINE monkeylearn
FROM monkeylearn

Once the ML_ENGINE is created, we use the CREATE MODEL statement to bring MonkeyLearn models to MindsDB.

For this example, you will make use of MonkeyLearn's pre-made model E-commerce Support Ticket Classifier.

CREATE MODEL mindsdb.ecommerce_ticket_classifier
engine = 'monkeylearn',
api_key = 'api_key',
model_id = 'model_id',
input_column = 'text';

On execution, you get:

ecommerce_ticket_classifierThe model name provided to the model created in MindsDB.
tagThe column that will provide the predicted result.
engineThe ML framework engine used, which is MonkeyLearn.
api_keyThe API Key of the model provided by MonkeyLearn.
model_idThe respective model's ID you want to make use of.
input_columnSpecifies the input column fed to the model

You can use the DESCRIBE syntax to verify the model's status.

DESCRIBE ecommerce_ticket_classifier;

On execution, you get:

Use the SELECT statement to make a prediction on the model.

SELECT * FROM ecommerce_ticket_classifier
WHERE text = 'Where is my order? The delivery status shows shipped. When I call the delivery driver there is no response!';

On execution, you get:

Create and train a model.

You can also create a model with a dataset. For this example, we will be using a dataset consisting of messages for E-commerce support tickets. The dataset will be uploaded as a file onto the GUI.

Use the CREATE MODEL syntax:

CREATE MODEL mindsdb.ecommerce_ticket_classifier2
FROM files (select * from queries2)
engine = 'monkeylearn',
api_key = 'api_key',
model_id = 'model_id',
input_column = 'text';

Use the SELECT statement to make a prediction

SELECT * FROM ecommerce_ticket_classifier2
WHERE text = 'I ordered 4 units but only received 3';

On execution, you get:

The MindsDB model created with the MonkeyLearn model successfully predicted the tag of an E-commerce support ticket according to the text input.

  1. What application can be built with MindsDB’s integration with MonkeyLearn?

Developers can build various front-end applications or automate workflows with MindsDB that can assist businesses with text extraction and classifications. MindsDB allows you to customise the application according to your business needs. Using E-commerce as an example, we can briefly explore the possibilty of building an application that can assist with streamlining the ticket routing process.

Companies receive E-commerce Support tickets in the form of emails or ticket logging applications, the data of these entries can be extracted using MonkeyLearn’s extractor,or any other extracting platform.

Once the data is extracted, you can make use of MindsDB’s API and integration with MonkeyLearn to develop a built-in Machine Learning model that classifies the E-commerce Support tickets. This solution can be integrated with ticket routing software that allows you to transfer the data that has been classified to that workflow.

These models not only assists with classifying the type of queries reported but can assist with the level of priority. It is also beneficial to your business’ reports and analytics that improves tracking KPI’s and measure performance against SLA’s.

You can check out more about MindsDB by visiting their documentation or Github Repository. Join the MindsDB Slack to be part of their community where you can share ideas and receive tech support.