Ntropy
Enabling companies to understand their customers through financial data.
The False Promise of General Transaction Categorization and the inadequacy of in-house models
The False Promise of General Transaction Categorization and the inadequacy of in-house models
Why the Ntropy customized model approach is the only solution for high performance
Using Elyra to create Machine Learning pipelines on Kubeflow
Using Elyra to create Machine Learning pipelines on Kubeflow
Customized Transaction Classification
Customized Transaction Classification
Successes, benchmarking, and how to maximize your performance. Bringing meta-learning to production.
Speeding up cross-encoders for both training and inference
Speeding up cross-encoders for both training and inference
At Ntropy (we’re hiring), we perform categorization on financial transactions over more than 150 different categories. We use NLP models…
How to Protect yourself from Advanced Phishing Scams (HTML injection)
How to Protect yourself from Advanced Phishing Scams (HTML injection)
This is a guest post by Ben Chinoy, a talented security engineer. He reached out to us about the security issue outlined below and…
Multilingual Named Entity Recognition for Financial Transactions
Multilingual Named Entity Recognition for Financial Transactions
How we were able to achieve the best accuracy for multilingual named entity recognition at Ntropy for financial transaction enrichment
Hiding endpoints from SwaggerUI while supporting with Connexion
Hiding endpoints from SwaggerUI while supporting with Connexion
Maintaining backwards compatibility is one side of the coin. The other issue is to make sure the new customers use only the latest version
Quickly finding recurring events in massive sequences
Quickly finding recurring events in massive sequences
A scalable O(N*K) solution for sequences of size N and max intervals of size K
Clustering millions of sentences to optimize the ML-workflow
Clustering millions of sentences to optimize the ML-workflow
At Ntropy, we deal with a large volume of financial transactions represented as plain text. We train models on these transactions from…
How we reduced our infrastructure costs by 8x without sacrificing performance
How we reduced our infrastructure costs by 8x without sacrificing performance
This blog post explains our journey in MLOps, describing how we leveraged the combination of open-source technologies and cloud providers…
Deep ML cannot be built in-house
Deep ML cannot be built in-house
We have heard multiple arguments over the last years that ML should be built in-house. From investors, customers, books and even candidates…
Transaction data is an uncut gem
Transaction data is an uncut gem
Transactional data is generated every time money is transferred between two entities, one initiating the transaction order and the other…
A castle getaway: the Ntropian offsite
A castle getaway: the Ntropian offsite
I am often asked about the why behind Ntropy. The truth is that it takes time to figure out your real why and what makes you tick. There is…
Understanding financial transactions
Understanding financial transactions
The term “transaction categorization” is widely used in financial services and in the broader software industry and is well-known in…
The Ntropy API
The Ntropy API
The Ntropy API enables companies to understand the financial transactions of their customers with super-human accuracy.
No-data ML
No-data ML
No-data ML allows models to obtain their data externally and be deployed to production without any in-house labels.