Subscribe
Sign in
Datrics — Create a better credit-risk model in days without coding
Datrics helps FinTech companies build and deploy machine learning models without writing code. Analysts and domain experts leverage a drag-n-drop interface to enable self-service analytics.
42
Replies
Kathy Zhou
congrats!
Share
The team behind this product is amazing and it deserves tons of upvotes, congrats guys!
Thanks @lindsayaamos for hunting us ♥️
Hey everyone, I am happy to announce a full launch of Datrics.
We're Anton, Kirill and Volodymyr, the founders of Datrics!
Datrics helps FinTech companies build and deploy machine learning models without writing code.
For instance, one of our customers is a consumer lending company that developed a new risk model using just our drag and drop interface.
I used to lead a large data science consultancy team, being responsible for Financial Services (and Risks specifically), where we’ve been working together with @volodymyr_sofinskyi. At some point of time we’ve realized that it usually takes months of work to turn an idea into a complete solution, going through data snapshot gathering to cleansing to experimenting to working with engineering and DevOps teams to turn experiments in Jupyter notebook into a complete application that works in production.
So we are here for two reasons:
1) Make the process much shorter
2) Make it available for analysts, engineers, risk modelers and domain experts, not only professional data scientists.
We’ve started working on the no-code machine learning platform for everyone: a tool to cover experiments and MLOps. Then the idea evolved and we’ve decided not to limit ourselves to machine learning.
We have broadened our aim to cover analytics process automation for advanced spreadsheet users, automate data prep visually and without coding, since spreadsheet analytics and data prep is as much time-consuming as advanced machine learning, and spending 400+ hours yearly on repetitive tasks is not unheard of. So we’ve built a cloud-native tool, with a simple and intuitive web interface and emphasis on ML components.
Over the last year, thanks to our amazing users, we’ve grown to a team of twelve and moved the product from alpha version to production and added tons of new features, and figured today would be a perfect time to launch on Product hunt! 🚀
We’re charging only for private deployments, so datrics web version is completely free here - https://platform.app.datrics.ai/... ! You can connect your data sources (DBs or CSVs), prepare your data and create your own models here. And even create your own bricks with a custom code if anything is missing!
There are advanced functions to intelligently fill missing values, do variable binning in a visual way - it is all covered in a specific template for Credit Risk, where you can see how it works on Lending Club data and adjust for your needs.
We're big believers in the power of Machine learning and self-service analytics, and we’re here to support the democratization of it! 🙌
Super-excited to hear your thoughts :). We gathered the wiki(https://wiki.datrics.ai) for the major Datrics functionality. The team and I will be around to answer your questions today and beyond, so comment here or reach out to me directly at av@datrics.ai!
Thank you, Stephanie! Btw, We planned marketing campaign optimization as a use case for implementation soon
@shaunacosby Hi Shauna, so very first one is credit risk modeling, e.g. probability of default. Building classic application scorecards is quite easy with our templates, and you can see accuracy Gini and API/what-if out-of-the-box. Other scenarios include sales aggreagation and reporting automation, demand forecasting and inventory management, predictive maintenance, in FinTech - AML, anomaly detection and transactional analytics. Happy to chat if you have some specific use case, maybe we'll be able to help - just drop me a note av@datrics.ai :)
