MODELS
Unlimited Basic subscription: unlimited Qwen 3.8 27B for €14.95/month, with no per-token billing

Industries / 10 / Services and public sector

Banking and financial services

From a financial report to data you can review.

Financial statement extraction, news sentiment analysis and internal policy search. Connect models to your organisation’s tables, documents and text.

Build structured outputs and sourced answers for analysis and operations teams.

Documents, knowledge, and automation

Statements, news, policies and requests.

Select a task with defined data and review criteria.

Financial statement extraction

Retrieve tables, amounts and periods from reports. Validate currency, scale and the relationship to the source page.

Financial news sentiment

Classify English financial text as positive, negative or neutral. Use labels as one signal within your analysis.

Internal policy copilots

Query procedures and policies using authorised sources. Filter by department, validity and team permissions.

Request and file classification

Organise submitted documents and extract workflow fields. Your application checks missing information and prepares the next task.

With QDivZero / Banking and financial services

Financial data with its table and reference.

Convert pages and tables into reviewable data or classify text with a financial model. Connect results to your systems; Retrieval supplies context for questions about policies and procedures.

One possible workflow

  1. Report or text
  2. Extraction or classification
  3. Validation and references
  4. Analysis system

Open-weight / Banking and financial services

Models for your industry

FinBERT for English financial sentiment; Granite Docling for document structure; embeddings and Qwen for retrieving and querying policies. Each covers a different task.

Financial sentiment · English

FinBERT

Classify English financial text as positive, negative or neutral.

Hugging Face referenceView model

Document conversion

Granite Docling 258M

For converting financial report pages and tables before extracting fields and validating figures.

Hugging Face referenceView model

Embeddings

Qwen3-Embedding-8B

For retrieving policies and procedures by department, permissions and document version.

View model

Text and vision

Qwen3.8-27B

For answering with internal policy context and preparing reviewable outputs from your documents.

View model

Banking and financial services

AI questions for Banking and financial services

What does FinBERT do and which language does the linked model support?

ProsusAI/finbert classifies English financial text into positive, negative and neutral sentiment. You can evaluate it with news or report passages. It provides a text signal for analysis; it does not calculate creditworthiness, credit risk or an investment decision.

How do I extract tables and periods from a financial statement?

Process pages with a document model and define the required data schema. Preserve headers, period, currency and scale alongside page references. Validate row and column relationships before consolidating amounts across documents or financial years.

Can I build an assistant over internal policies and procedures?

Index sources with department, version and permissions, then retrieve passages relevant to each query. An LLM can prepare a referenced answer. Your application controls access and connects tools when it needs current operational data.

How do I classify submitted documents to prepare a file?

Define workflow-related categories and fields, such as document type, date or identifier. Evaluate incomplete formats and unknown types. The application validates results and prepares the next step; retain originals so the team can review classification or extracted data.

Which models do I need for financial document and news analysis?

Separate tasks: a document model retrieves structure and tables; FinBERT supplies English sentiment; embeddings retrieve passages; an LLM prepares contextual answers. You can combine components without assuming one model performs numerical analysis, search and classification equally well.

How do I estimate the cost of an AI application for financial services?

Separate document preparation, retrieval, inference and tool integration. Estimate volume, concurrency and context for each workflow: classifying requests differs from analysing long contracts. Compare configurations with real examples and include result validation and review.

Can I connect an assistant to my CRM or ERP?

Your integration can expose authorised queries through tools using those systems’ APIs. The model requests a tool and your application validates and executes the call. Limit accessible data and distinguish queries from actions that change records.

Can I use custom models for specialist financial workflows?

You can deploy compatible private or fine-tuned models and connect them to your application. Evaluate formats, context and instruction following with workflow examples. If the goal is querying changing documentation, also compare a Retrieval solution before deciding how to adapt the model.

How do I decide which AI results can proceed automatically?

Define workflow-specific validation: required fields, consistency of amounts, references and permitted actions. Test incomplete inputs and ambiguous cases. Your application uses these criteria to proceed or request review; a well-written answer alone does not validate a value or operation.

Start with one report or analysis workflow.

Compare extraction, references and formats using your organisation’s documents before expanding the workflow.