FAQ.

How can I start working with Vanti?

It’s very easy!

The best way to start is to schedule a demo with us.

What kind of insights can I expect?

Vanti analyzes your data to understand the underlying model and produce actionable insights about

Root cause analysis
Opportunities to improve performance
Zero in on the most important parameters
Reduce testing scope & time
Accurate data-driven predictive models
interactions/relationships between parameters and features within your data

For more info subscribe to our newsletter

‍

Who should use Vanti?

Vanti is designed specifically for operations professionals in digitized manufacturing facilities

Do I need a data scientist to use Vanti?

No!
Vanti is your personal automated data scientist, ready to answer any question you have regarding your data and to provide actionable insights. Just upload the data and Vanti’ll do the rest.

What is a Model and what is a “KPI”?

A Model is a single relationship between 1 parameter (the “KPI”) and all other parameters.
You can build how many models you wish based on a single data set, each will have its own model and insights.

What kind of data is supported?

Data types of all kinds (numbers, text, binary, etc.) are fully supported.

For updates sign up for our newsletter

What’s the minimum size of a dataset for insights?

For a deployable model, we usually recommend a dataset from a repeatable / established process or manufacturing line.

For quick analysis & insights, you can use even small data sets from batch testing.

How is the model deployed?

Full SaaS solution

Each model created can be deployment as an endpoint on the cloud.

How can Vanti increase production line throughput?

Each model created can be deployment as an endpoint on the cloud.Vanti helps increase line throughput by predicting faulty units early in the process, using proprietary prediction algorithms. This helps reduce the time & effort that would otherwise be invested on failed units, making the production line work more efficient and producing more good units in less time, thus increasing throughput.

How can Vanti reduce the cost of failure?

Cost of failure consists of the time & effort required to produce a faulty unit. By applying Vanti’s prediction-based models in real-time, Vanti will be able to filter out faulty units early in the process, removing the need to continue and invest more time & effort on them, thus, reducing the total cost of failure.

How long before I see a throughput increase and cost reduction by using Vanti?

Thanks to Vanti’s rapid deployment, models can be created, configured, trained and deployed in a matter of just a few hours. Once deployed, integrating the model to the production line to get real-time predictions can be done immediately. In a matter of just a couple of days, you will be able to experience an improvement in production line performance.

What do I need to know in order to use Vanti in my production line?

Once you have decided what is the use case you wish to implement using Vanti, you will be asked to provide the data upon which the model will be built. To review the model performance, you will need to know to measure its performance. Vanti offers clear and concise metrics to do just that, without getting bogged down with the technical details.

To enable real-time prediction, you will need to integrate the model with the production line. This will be a one time effort that would require technical knowledge.

Can I customize the model to fit my specific business needs?

Yes. Vanti offers domain expert customization that can be infused to the model creation itself. This allows the creation of models that favor precision at the expense of recall, for example. Of course, you don’t have to do any of that if you don’t feel comfortable with it. Instead, Vanti would create the best model for you, based on industry standards.

Can you use data that is generated from any machine in the production line?

As long as the machine generates data, Vanti can use it to help build a prediction model. Vanti is machine agnostic, meaning it only takes the data coming in from the production line, regardless of which machine generates the data, and predicts a result based on it.

What happens if the data I send to Vanti is changed?

Data coming from production lines change frequently, due to changes in the tests being conducted, changes in the material itself and other external factors. Being aware of it, Vanti offers its customers something that is called “model resiliency”. In essence, that means that every time data is changed in the production line, Vanti would test the deployed model to make sure that it can still provide accurate predictions and that the performance of the model has not deteriorated. Only if this is the case, Vanti will keep making real-time predictions; otherwise, Vanti would halt its real-time predictions and suggest creating a new model that would fit the new data structure.

How will Vanti make sure it won't cause damage to my production line with wrong predictions?

Vanti AI models not only make real-time predictions, but it also offers built-in fail-safe mechanisms that ensures the model performance is at its very best. Vanti constantly monitors each model performance and proactively defends against performance degradation, by detecting and alerting this to the user and by halting predictions if found necessary.

How are new models built and created?

Models are created through a self-service platform and require no coding. They can be deployed as supervised or unsupervised models. All models are optimized and reviewed before deployment.

What is the data structure I should upload to create a model

For tabular data, you should upload a file where each row represents a single unit and each column represents either a test result or a measurement that was recorded for every unit.

For image-based data, you will need to upload a set of images that you wish the model to learn and be able to detect anomalies.

What is considered to be enough data to create a model?

Generally speaking, you would need to have at least 1000 units in the dataset, both for tabular and image-based data.

For tabular data, the rule of thumb is to have 10 units recorded for each column. For example, if you have 100 columns in the dataset, you should have at least 1,000 units (i.e. rows) recorded.

How are prediction models managed?

All of the data, insights, and configurations for your prediction models are accessible through our SaaS platform.

FAQ.

NEWSLETTER

Subscribe to receive the latest updates!

Want to learn more?