How to use Aito in your projects.
Aito is for those who need fast-to-deploy non-narrow machine learning. For developers that care about fast time to market and have no access to data science resources. Or simply are after best bang for their buck and want to maximize their AI ROI.
Aito is faster to use than TensorFlow, more intelligent than Elasticsearch, yet easy and familiar like SQL.
As part of the IKEA Open Innovation program 2019, Aito created a demand simulator for IKEA.
The demand simulator recognizes the different features of the new products, compares them to the historical data of products already in the assortment, and estimates how big the demand will be. Changing certain features (e.g. colors, material or size) simulates how the demand will change, and why.
The augmented results, generated by Aito’s predictive database, will assist the demand planner in better understanding and better estimating the demand. The MVP was created in a timespan of 5 weeks.
Augmented results to help you make better demand forecasts of new products.
Together with Korkia we allow you to easily deploy RPA. You can automate repetitive tasks such as invoice handling, reducing the chance of mistakes and improving process efficiency.
With 250 training examples, we got a 77% accuracy rate in invoice categorization. More details on the blog post: Using a predictive database for AI-enabled RPA.
Free employees from error-prone chores and focus on the core tasks within your organisation.
Smart search allows you to get easy access to heterogeneous and scattered documentation throughout your organisation. Think of internal chat channels, online tutorials, customer support issues, project management information.
Aito works great with both structured and unstructured/unlabelled data, which can be text, documents, numbers, events and behavioral data. Read more about it on our blog post: How agile AI experiments can help to identify who knows what within big organisations.
Uncover who knows what within your organisation, with no taxonomy or tagging needed.
Intwixt helps customers design business workflows that can be deployed to messaging apps like Slack or Messenger. When creating a conversational UI, it is important to accurately interpret the user’s intent, without impacting the user experience negatively.
Contextual awareness is key to solving usability challenges and this is where Aito shines. If, for example, you need to collect multiple fields of information from a user, you can use Aito to predict what the user will most likely say. Instead of prompting the user to enter successive inputs, the app can prompt them once to confirm what they’ll most likely do.
Aito’s APIs make it easy to train the model and increase predictive accuracy. Read more about it on our blog post: Building intelligent Slack workflows.
Intwixt was able to integrate Aito to their platform in one day. It's a great enhancement to usability without having to develop and manage complex ML models themselves.
Aito allows you to predict churn from time series and, apart from the predictive part, will also return explainable results.
These explainable results will help to anticipate and to decrease the churn rate.
Additionally, the Recommend API endpoint can also be used to recommend the most suitable action to prevent a possible churn. Read more about it on our blog post: Using time series forecasting for predicting Freska's customer churn.
Using Aito resulted in a +10% gain in churn prediction accuracy. The explainability helped to provide insights on why a customer might be churned and direction on how to continuously improve the model.