Assess Risk In Financial Portfolios

Intro

Portfolio risk analysis with UP42

Hurricanes, earthquakes, floods, and forest fires are extreme weather events that are becoming more frequent. In addition to tragic human losses, proximity to such natural disasters pose a significant risk to financial assets and liabilities. Geospatial data and analytics can provide actionable insights to help balance and neutralize that risk.

Overview

High-resolution imagery and weather data

Access high-resolution Sentinel-2 optical imagery for vast areas of interest. Augment analysis with 1000 historical and forecasted weather parameters.

Predict water-related geohazards

Use out-of-the-box machine-learning algorithms processing Sentinel-2 data to predict flooding or exposure to water bodies for your areas of interest.

Gain a holistic view of portfolio risk

Combine weather and geohazard predictions with your own algorithms applied to high-resolution satellite, radar, or aerial data to get a full picture of your portfolio risk.

Benefits

Benefits for you

Save costs by purchasing only the data and processing the algorithm covering exactly your customer's AOI.
Save time by utilizing our APIs to automate your analytics workflows fully.
Avoid costly and time-consuming setup by building on our tried-and-tested infrastructure.
Supplement archive data with the latest data, utilizing our bespoke tasking service.

Benefits for your customers

Get timely insights to proactively respond to portfolio risk, enabling you to divest or balance your portfolio effectively.
Ensure you have a full picture of portfolio risk, utilizing various high-quality data sets and analytics.
Avoid adding another software platform to your stack. Receive insights directly in existing tools via API.

Build your solution with UP42

Portfolio risk analysis for:

Insurance and Financial Services

Identify risk areas in your financial portfolio, whether that is due to, for example, commodity supply or natural disasters.

Real Estate

Predict water-related geohazards to identify areas of your real estate portfolio that is at risk of damage and financial loss.

The technical details

How can you use UP42 to build portfolio risk analysis solutions?

Data

High-quality satellite imagery

Access the latest Sentinel-1 and Sentinel-2 imagery, searching via our catalog search feature that enables you to search based on cloud coverage and date range. Supplement the Sentinel-2 imagery with a range of weather data parameters that can provide historical and forecast information on extreme weather risks.

Historical analysis

Apply algorithms to vast archive data

Map historical flooding by processing Sentinel-1 SAR data over time and automatically identify areas that have been at high risk of flooding. Additionally, process Meteomatics' weather data to detect regions that are prone to extreme fluctuations in wind speed, rainfall levels, and temperature that all indicate susceptibility to extreme weather events.

Predictions

Predict water-related geohazards

Use Platoi's Advanced Water-Related Geohazards processing block on Sentinel-2 imagery to predict areas at risk of flooding and exposure to water bodies. With predictions up to six months in advance, this block can provide adequate time to respond to portfolio risks through divestment, alternative investment, or risk balancing tactics.

API

Combine and integrate your insights

These ranging insights from the identification of extreme weather to historical flood maps to water-related geohazard predictions can be easily integrated into geospatial products via API or downloaded and provided directly to the end-user. In addition to the ease of integration, the API and Python SDK enable this analysis to run regularly and feed into legacy tools or alert systems.

Access our Python SDK

import up42
up42.authenticate(project_id="12345", project_api_key="12345")
project=up42.initialize_project()

workflow = project.create_workflow(name="Portfolio", use_existing=True)
input_tasks=['sentinelhub-s2-aoiclipped', 'advanced-water-related-geohazards-predictor']
workflow.add_workflow_tasks(input_tasks=input_tasks)
parameter = workflow.construct_parameters(
    geometry=[13.41686, 52.51167, 13.422503, 52.514706],
    geometry_operation="intersects",
    start_date="2020-01-01",
    end_date="2020-10-14",
    limit=2)

job = workflow.run_job(input_parameters=parameter, track_status=True)
job.download_results()

Use Case