Cyprus Job Market Visualiser GitHub

This is a research tool that visualizes 39 ISCO-08 occupation groups from Eurostat and HRDA/AnAD data, covering the Cyprus labour market. Each rectangle's area is proportional to total employment. Color shows the selected metric — toggle between projected growth outlook, median pay (EUR), education requirements, and AI exposure. This is not a report, a paper, or a serious economic publication — it is a development tool for exploring Cyprus employment data visually.

LLM-powered coloring: The source code includes data pipelines, parsers, and a framework for writing custom LLM prompts to score and color occupations by any criteria. You write a prompt, the LLM scores each occupation, and the treemap colors accordingly. The "Digital AI Exposure" option is one example — it estimates how much current AI (which is primarily digital) will reshape each occupation. But you could write a different prompt for any question — e.g. exposure to humanoid robotics, offshoring risk, climate impact — and re-run the pipeline to get a different coloring.

View the Digital AI Exposure scoring prompt (example)

You are an expert labour market analyst evaluating how exposed different occupations are to AI. You will be given an occupation description based on the ISCO-08 international classification, in the context of the Cyprus and EU labour market. Rate the occupation's overall AI Exposure on a scale from 0 to 10. AI Exposure measures: how much will AI reshape this occupation? Consider both direct effects (AI automating tasks currently done by humans) and indirect effects (AI making each worker so productive that fewer are needed). A key signal is whether the job's work product is fundamentally digital. If the job can be done entirely from a home office on a computer — writing, coding, analysing, communicating — then AI exposure is inherently high (7+), because AI capabilities in digital domains are advancing rapidly. Conversely, jobs requiring physical presence, manual skill, or real-time human interaction in the physical world have a natural barrier to AI exposure. Consider the Cyprus/EU context: tourism and hospitality are major employers, financial services and shipping are key sectors, the EU Digital Decade targets drive digital skills demand, and the public sector is proportionally larger than in other economies. Use these anchors to calibrate your score: - 0–1: Minimal exposure. Examples: agricultural labourer, construction labourer, commercial diver. - 2–3: Low exposure. Examples: electrician, plumber, firefighter, building trades worker. - 4–5: Moderate exposure. Examples: health associate professional, police officer, personal care worker. - 6–7: High exposure. Examples: teaching professional, manager, business administration professional. - 8–9: Very high exposure. Examples: ICT professional, legal professional, business/admin associate professional. - 10: Maximum exposure. Examples: general clerk, numerical recording clerk, data entry operator. Respond with ONLY a JSON object in this exact format, no other text: {"exposure": <0-10>, "rationale": "<2-3 sentences explaining the key factors>"}

Caveat on Digital AI Exposure scores: These are rough LLM estimates, not rigorous predictions. A high score does not predict the job will disappear. Software developers score 9/10 because AI is transforming their work — but demand for software could easily grow as each developer becomes more productive. The score does not account for demand elasticity, latent demand, regulatory barriers, or social preferences for human workers. Many high-exposure jobs will be reshaped, not replaced.

Layer

Declining

Growing

Total jobs

—