Financial NLP · On-device

Read the market before you finish the headline.

FinSense scores financial text as bullish, bearish, or neutral in 42 microseconds — on your own device, in four languages, with no cloud round-trip and no one watching your queries.

90.8%

FiQA financial sentiment

233 MB

INT8 ONNX · DeBERTa-v3

42 μs

Inference · Snapdragon X2 Elite

4

Languages — EN · ES · ZH · JA

What it is

A sentiment model that lives on your hardware.

DeBERTa-v3, distilled to the edge. Three-class financial sentiment — accurate, private, instant.

On your device

Runs locally as a 233 MB INT8 ONNX model — desktop, server, or modern phone. No round-trip, no rate limit, no per-call fee.

Your queries stay yours

Nothing is sent to a third party. The headline you score never leaves your hardware.

Cloud API, your choice

A REST API for teams that want it server-side — same model, same numbers, your infrastructure.

Four languages, natively

English, Spanish, Chinese, and Japanese — financial sentiment trained per-language, not machine-translated.

Measured, not claimed

Three public benchmarks. Real numbers.

88.2%

Financial PhraseBank · 50agree

hardest split · held-out · ties FinBERT (87.8%) at half the size

98.28%

Twitter Financial

bullish / bearish / neutral · 2,388

90.84%

FiQA

headlines + microblogs · 961

Put FinSense to work.

On-device or API. Paper-test first, deploy on your own hardware when you’re ready.

Get notified when new capabilities ship