Innovation<br/>Lab

Cutting-edge research on conversational ERP, GenAI document understanding, predictive finance, and AI governance. Open benchmarks, model cards, and experimental prototypes.

Active Research Areas

Six tracks pushing the boundary of what's possible in enterprise finance AI

Beta

Conversational ERP Interface

Beta Q2 2025

Natural language → SQL → Action. Transform how users interact with ERP systems through chat.

NL-to-SQL: 92% accuracyComplex joins: 67%Latency: <2s p95RLS enforced at query layer
Team: 4Papers: 3
Production

GenAI Document Understanding

GA v2.0 H2 2025

Next-gen document intelligence: multi-modal, multi-language, layout-aware, context-rich extraction.

Accuracy: 99.5%+Formats: 25+Languages: 15+Layout understanding: Yes
Team: 6Papers: 5
Pilot / Beta

Predictive Finance Models

GA Q3 2025

Cash flow, revenue, expense forecasting with explainable AI. Ensemble models on ERP transaction graphs.

30-day accuracy: 92%90-day accuracy: 87%Features: 200+SHAP explainability: Yes
Team: 5Papers: 4
Pilot / Beta

AI Governance & Compliance

GA Q4 2025

Automated EU AI Act compliance, model monitoring, bias detection, and audit-ready documentation.

Risk classification: AutoMonitoring: Real-timeBias tests: 12 dimensionsAudit trails: Immutable
Team: 3Papers: 2
Research

Agentic Workflow Orchestration

Research preview 2026

Multi-agent systems for end-to-end finance processes. Planning, execution, verification, and self-correction.

Agents: 5 specializedSuccess rate: 78%Self-correction: 3 retriesHuman-in-loop: Configurable
Team: 4Papers: 1
Research

Multimodal Finance Understanding

Exploratory

Vision + language models for financial documents: charts, tables, handwritten notes, stamps, signatures.

Chart extraction: 89%Table structure: 94%Handwriting: 82%Stamp/seal detection: 91%
Team: 3Papers: 2

Open Benchmarks

Reproducible, transparent benchmarks for finance AI. Data, code, and methodology open-sourced.

Published2024-07

Invoice Extraction Benchmark

50,000 invoices across 15 formats, 8 languages. GenAI vs OCR vs Human baseline.

GenAI: 99.2%OCR: 87.3%Human: 99.8%
Published2024-11

AP Automation ROI Benchmark

237 production deployments. Processing time, cost/invoice, automation rate by platform/volume/industry.

Top quartile: 3 minMedian: 45 minCost range: $0.85-$8.75
In Progress2025-Q1

Text-to-SQL for Finance

Spider + custom finance schema. 1,200 NL questions → SQL. Executable accuracy + semantic correctness.

Simple: 94%Medium: 87%Complex: 67%Finance-specific: 82%
Planned2025-Q2

Exception Handling Benchmark

10,000 exception cases. AI-native vs Rule-based vs Human resolution time and accuracy.

AI-native: 2.3 minRules: 12 minHuman: 18 minAccuracy: 94% vs 78%

Publications & Thought Leadership

Peer-reviewed papers, whitepapers, and technical articles from our research team

ArticleJuly 2024

GenAI vs OCR: Invoice Processing Accuracy Showdown

Flowtaris AI Research Blog

Authors: Dr. James Park, Dr. Sarah Chen

ReportJanuary 2025

State of AI Automation in Enterprise Finance 2025

Flowtaris AI Annual Report

Authors: Dr. Sarah Chen, Marcus Rodriguez

PaperAugust 2024

Conversational ERP: Natural Language Interfaces for Enterprise Systems

VLDB 2024 Workshop

Authors: Dr. Alex Kim, Dr. James Park

PaperMay 2024

Benchmarking Document Intelligence for Financial Workflows

ICDE 2024

Authors: Dr. James Park, Priya Sharma

WhitepaperSeptember 2024

EU AI Act Compliance for Finance AI Systems: A Practical Framework

Flowtaris AI Whitepaper

Authors: Elena Volkov, Dr. Alex Kim

Lab Team

Researchers, engineers, and domain experts pushing finance AI forward

AK

Dr. Alex Kim

CTO & Lab Director

Focus: Conversational ERP, Agentic Systems

SC

Dr. Sarah Chen

Chief Research Officer

Focus: Finance AI Benchmarks, ROI Modeling

JP

Dr. James Park

ML Research Lead

Focus: Document Understanding, Multimodal

MR

Marcus Rodriguez

VP Analytics

Focus: Predictive Finance, Benchmarks

EV

Elena Volkov

AI Governance Lead

Focus: Compliance, Risk, EU AI Act

PS

Priya Sharma

Solutions Architecture Lead

Focus: Production ML Ops, Integration

Get Involved

We collaborate with academia, industry partners, and open-source community

Open Source

Contribute to our benchmarks, models, and tools on GitHub

Research Collaboration

Partner with us on joint research, benchmarking, or academic publications

Join the Team

We're hiring ML researchers, engineers, and finance domain experts

Join the Design Partner Program

Get early access to pilot capabilities, influence product roadmap, and co-design with our research team

No spam. Unsubscribe anytime. Read our Privacy Policy.

Stay at the Frontier

Monthly updates on new research, benchmark results, open-source releases, and lab experiments. No spam.

Read our Privacy Policy.