Java-native AI, proven in production.
From payment fraud to particle physics – teams run Deep Netts where their systems already live: inside the JVM. Four real deployments, each without adding a second stack.
Real-time fraud detection inside the transaction flow
- Problem
A payments platform needed to score every transaction for fraud in real time – but routing traffic through a separate Python scoring service added latency, infrastructure, and a second stack to operate.
- Solution
Deep learning models built with Deep Netts run directly inside the Java transaction pipeline. Scoring happens in-process, with no network hop and no additional runtime to deploy or monitor.
- Outcome
Fraud decisions now land in milliseconds, inside the same JVM that processes the payment – and the fraud team iterates on models with the tools the platform team already runs.
- 0
- Scored
- 0
- Approved
- 0
- Blocked
- 0
- Last score
Every payment passes through the platform's Java service. Fraud is a small fraction of them, and its patterns keep changing – rules alone are easy to bypass.
Case: payments platform, not named – 30%, ms and 0 from the case. Features, model, 0.70 threshold, benchmark and test results: Deep Netts talk “AI in Java for the Financial Industry”, Amsterdam JUG at ING, Oct 2026 (an example model, not the customer's). Payments drawn are illustrative.
Forecasting cloud resources before the bill arrives
- Problem
An enterprise platform team was over-provisioning cloud capacity to stay safe, because usage forecasts were coarse and reactive – and the cost of that safety margin kept growing.
- Solution
Deep Netts models forecast resource demand from historical usage, running natively inside the team's JVM-based tooling. Predictions feed autoscaling and capacity planning directly, with no separate ML pipeline.
- Outcome
Provisioning now follows predicted demand instead of worst-case guesses, cutting spend while improving stability during load spikes.
- –
- Month
- –
- Demand vCPU
- –
- Capacity vCPU
- –
- Idle
Without a usable forecast, capacity is sized for the worst case and kept there all year. Most of it is paid for and sits idle.
Enterprise IT customer, not named. The 15–25% figure is from the case; demand, forecast and capacity drawn here are illustrative.
Predicting particle trajectories with neural networks
Read the full story- Problem
Every event in the CLAS12 detector leaves many segments in the drift chambers – from real particles and from background. The conventional algorithm has to try their combinations, tracking takes 80–90% of event processing time, and at high beam intensity good tracks get lost among the candidates.
- Solution
Two neural networks built with the Deep Netts community edition, in Java, inside the lab's Java reconstruction software: a multi-layer perceptron that labels each track candidate a positive, negative or false track, and an auto-encoder that fills in a segment a chamber missed.
- Outcome
On real data, 15.6% more reconstructed tracks – over twice as many with a missing segment – and 35% faster tracking. Physics analyses gain 15–35% more events (G. Gavalian et al., arXiv:2202.06869).
- 0
- Segments
- 0
- Candidates
- 0
- Rejected
- 0
- Tracks found
A 10.6 GeV electron beam hits a 5 cm liquid-hydrogen target. This event has an electron and two pions – one of the reactions the paper analysed.
Source: G. Gavalian et al., CLAS12 Track Reconstruction with Artificial Intelligence (arXiv:2202.06869) – detector layout, network, two-pass workflow, Table 1, run conditions. The event drawn is illustrative.
- Problem
High-throughput screening produces tens of thousands of data points in one session. Finding the compounds that cause the desired change in a protein calls for deep learning – but tools that depend on native libraries are hard to run on specific hardware, and QSAR methods need structural data such as SMILES that many library compounds lack.
- Solution
Oscar Bastidas, Ph.D., analyses the screening data with Deep Netts feed-forward networks in Java, trained on the physical and chemical properties already in the compound library, with hyperparameters tuned to the data. His study of spike-protein dynamics with Zoran Ševarac, analysed in Java, was published in Scientific Reports (2024).
- Outcome
Hit identification runs entirely on the JVM – no native dependencies, no QSAR input, and in the language the researcher already works in.
- 0
- Frames
- 0
- Top frequency
- 0
- Screened
- 0
- Hits
The study simulated the SARS-CoV-2 spike protein (PDB 6VSB) in water for 200 ns, one frame per nanosecond. From every frame the backbone angles φ and ψ of each residue are read – here φ of one residue.
- Protein dynamics
- Screening with Deep Netts
Sources: O. H. Bastidas & Z. Sevarac, Time dependent dihedral angle oscillations of the spike protein of SARS-CoV-2, Scientific Reports (2024); O. Bastidas, Ph.D., Deep Learning in Drug Discovery (2021). The protein fragment, compounds and values drawn are illustrative.
Have a workload like these?
Tell us about your system – we'll show you how Deep Netts fits inside it.