What
are we building?

Aim

Our aim is to develop an
automated
way to
quantify
net impact
of
companies
on
people, planet,
society and knowledge.

Approach

We are building something many think is impossible. It's ok.

Our approach for building our quantification model is:

Iterative

The model will never be ready. Rather we build a new version practically every week. New products, research and companies emerge every day, and that is pretty cool. We are happy that already now, in our project’s infant phase, we are able to produce information and understanding that to our knowledge no other system can. However, the road ahead of us keeps us humble and excited.

Fiercely practical

The model will never be perfect. All models and numerical representations are just proxies, they ARE not the truth. A perfect model accurately depicting all impacts of all companies in real-time is theoretically impossible. However, a net value creation measuring system significantly better than the one at use today CAN be done. Not being able to build something perfect is a lousy excuse for not doing better.

Collaborative

We want to put together all the work of millions of researchers by using scientific articles as our main input data. Also, we want to build a system where everyone who wants to contribute to the building of better understanding of what companies achieve can do so. Our aim is to help people collaborate in making more fact-based decisions.

See CONTRIBUTE  ⟶

“Big stuff only”

This is our dearest design principle throughout the model. It means we only concentrate on the largest impacts a company has on the surrounding world. It’s the only way to stop losing sight of the Tier 1 priorities (e.g. fighting climate change) in Tier 2-10 data (e.g. whether or not your company serves cool artisanal coffee). Also, it’s a great way to stay sane. Practical example: for an oil company, we don’t care whether or not they use recycled office paper.

Uses

What is our model good at?

Our net impact model is built for…

Analyzing and optimizing large groups of companies (e.g. investment portfolios).

  • Our model is good at looking at the big picture and summarizing information that would otherwise be very difficult or impossible for human brains to grasp.
  • It helps answer questions such as “Which funds actually fight climate change in the most effective way?“ or “What should I invest in if I want to maximize my impact on creating new knowledge while, at the same time, keeping my environmental impact net positive?”

Making comparisons between products or companies.

  • It helps answer questions such as “If I want to work in marketing and contribute the most to health of people while keeping my GHG emissions low, which of these companies ranks the highest for me?”

Understanding the scale of impacts.

  • Our model helps understand what is big and what is not. It also forces the user to be explicit about their values: decide what they are optimizing instead of just talking about "good" or "bad" business.

Our net impact model is
not
built for…

Dividing companies into good and bad ones.

  • We don’t believe in certificates for morally superior companies as an effective tool for driving real change. We believe in calmly looking at facts without jumping to conclusions: what does this company get done and with which resources? With our net impact model, we aim to raise discussion about what companies really achieve, and facilitate a step change in thinking of value creation of companies.

Comparing two brands of the same product with largely similar impact.

  • Our model is not meant for answering questions like “Should I buy my soda from Pepsi or Coca Cola”. If their product mix, employee count and size are similar, they get a similar net impact score.
  • This boils down to the granularity of our product taxonomy: if two products have significantly differing impacts (e.g. sugar-sweetened soft drink vs. artificially sweetened soft drink), they are listed as different products in our taxonomy. If not, then they are the same.

Logic

The Upright model aims to build a big picture of what kind of value companies create. Our approach can be simplified to being built on three inputs: an understanding of what kind of products and services exists, a list of all the ways a company can impact the world around it, and scientific journal articles as source data for understanding about relationships between the two.

Basic logic of our quantification model

1
Taxonomy of all products and services
2
Structure of main impacts of companies
3
Database of 80 million scientific articles
Magic AI
Automated summary of impact of all products and services
How can we gain understanding of all products and services from scientific articles, while there are hardly any studying the impacts of, let’s say, pencils? The answer lies in how our taxonomy is built: the products form a network with links to one another.

How is the Upright
product taxonomy
built?

Rather than being individual items, products form a network
Products are linked to each other in two ways:
1
According to
product family hierarchies
(e.g. “apple” is a child of “fruits” and a parent of “green apple”)
2
According to
value chain parts
(e.g. “apple farmer” buys pesticides from “pesticide company” and sells its apples to “fruit wholesaler”)
Below you can see an example about product family hierarchies for an apple:

How does the Upright
product taxonomy
work?

ParentPlant-basedproductsParentFruitsParentPome fruits andstone fruitsProductAppleChildGreenappleChildRedappleChildYellowapple
Example: apple
Example of logic: If there is scientific knowledge that consumption of “plant-based products” contributes positively to the treatment of type 2 diabetes, “green apple” inherits that positive impact.
A product
inherits impacts
from
1) All its children
2) The parents on its particular path
We also want to make sure that value chains are taken into account. This means that, for example, the GHG emissions caused in mining shouldn’t just be the mining companies’ headache - but also partly allocated to all industries who use the metals and minerals that are dug up. Again, an example for “apple”:

Products are also linked to each other according to their position in
value chains

UpstreamInternalDownstreamSupplierPesticidesSupplierTractorSupplierApple treefertilizerProductAppleCustomerFruitwholesalerCustomerBakeryEnd user…eating apples
Upstream: Impacts caused by suppliers of a product or service
Internal: Impacts caused by internal operations when manufacturing a product or providing a service
Downstream: Impacts caused by using a product or service
Our second input is a structure of the most significant ways a company can impact the world around it. The impact structure is modular (impacts can be added and removed using value sets) and constantly iterated with experts.

The upright model considers 19 impact categories in 4 dimensions

Impacts (negative or positive)
Environment
  • GHG emissions
  • Non-GHG emissions
  • Biodiversity
  • Fresh water
  • Waste
Health
  • Diseases
  • Diet
  • Physical activity
  • Relationships
  • Meaning & joy
Society
  • Taxes
  • Jobs
  • Societal infrastructure
  • Equality
  • Societal stability & understanding among people
Knowledge
  • Scarce human capital
  • Knowledge infrastructure
  • Creating knowledge
  • Distributing knowledge

Now comes the tricky part. We need data about the impacts that the products and services have on the environment, health of people, society and creation and distribution of knowledge. This is where we need our engineering skills: to teach a neural network to understand causalities in natural language, i.e., the scientific articles.

Over the last 6 months, we have built a pretty exceptional training data set of over 30 000 scientific articles which we have read and classified manually to train the neural network.

How are causalities read by a machine?

Overview of Upright's ML-based article classifier

After getting the raw data from the neural network, we form scores for each combination of product and impact using an algorithm that combines information about 1) the prediction distribution, 2) number of articles studying a particular product/impact pair, 3) position and relative relevance of the product in its value chains, and 4) position and relative relevance of the product in its product family hierarchies.

After this, we have the basic building blocks for forming net impact profiles for all products and services. By summing these up, we get companies - which we can further sum up to form portfolios, funds, industries and other entities whose impact we wish to understand.

And that’s it! It’s a pretty crazy exercise, but we really believe this is problem worth fighting for. This is our first effort towards solving it. We invite you to follow our progress, cheer us on, contribute and/or build your own solutions!

Explore

We want to make our model open access and free to use for employees and consumers. In the meanwhile, you can take a sneak peek of its current status via these videos.
Why is the current impact discourse not enough?
It’s time we take the discussion to the next level.
The net impact of cigarettes and sewers
Take a sneak peek into how the Upright model works in practice.
Helping investors put their money where their values are
Moving from compliance data to understanding the actual impacts of products and services.