JUST Capital and The Data Incubator Challenge

Data Science For Social Good (1)


Today, we’re excited to announce that we’re teaming up with JUST Capital to help crowd-source data science for social good.  The Data Incubator offers a free eight-week data science fellowship for those with a PhD or a masters degree looking to transition into data science.  As a part of the application process, students are asked to submit a data science capstone project and the best students are invited to work on them during the fellowship.  JUST Capital is helping providing data and project prompts to harness the collective brainpower amongst The Data Incubator fellows to solve these high-impact social problems.

  • These projects focus on applied data science techniques with tangible impacts on JUST Capital’s mission.
  • The projects are open ended and creativity is encouraged. The documents provided, below, are suitable for analysis, but one should not shy in seeking out additional sources of data.

JUST Capital is a nonprofit that provides information and rankings on how large corporations perform on issues that matter most to the public. We give individuals a voice on what really matters to them, and evaluate how companies perform on those issues. By providing the right knowledge and making it easy to access and understand, we believe capital will flow to corporations that are more JUST, ultimately leading to a balanced business world that takes into account human needs that are so often neglected today. The meaning of JUST is defined by the American public as fair, equitable and balanced. In 2016, JUST Capital surveyed nearly 4,000 Americans from all regions and walks of life, in its second annual Poll on Corporate America. The issues identified by the public form the basis of our benchmark — it is against these Drivers and Components that we measure corporate performance. The most important factors broadly relate to employees, customers, company leadership, the environment, communities and investors.

JUST Capital has assessed and ranked 897 of the largest publicly-traded companies in America. These companies are the majority of the constituents in the Russell 1000 Index, which represents about 92% of the U.S. stock market value. We’ve excluded only those that we can’t subject to a common standard of measurement, such as most REITs, companies that do not file form 10K with the SEC, or investment holding companies. The number of ranked companies may change due to corporate activities such as mergers and acquisitions. We may also exclude companies from the rankings due to data limitations, such as having a relatively small US employee headcount. Additionally, for the inaugural release of company rankings, scores and rank for the bottom 50% of companies are strictly confidential. In late 2017, JUST Capital will release a full head-to-head rank of the largest publicly-traded companies in America.

Background Documents

  • Metric Legend: metric_table.xlsx. This document provides an overview of the ranking mode performance indicators or metrics. Metric codes, used in subsequent projects, as well as metric definitions, can be found within this document. Metric codes are somewhat self-explanatory (e.g., PAY.LIVING refers to a score per company on the percent of employees making a living wage in the county in which they work; JOBS.US refers to a score on job creation in the United States).
  • JUST Capital Methodology. The JUST Capital Methodology is a comprehensive view of the JUST Capital ranking and scoring framework. The methodology dives into particular detail in Section 4.2. In summary, companies are compared only against industry peers (this will change in 2017). A Z-Score was used, with 50 as the mean and 25 as one standard deviation.
  • For files that require a password, please use: tdi

You can apply to The Data Incubator fellowship here: https://www.thedataincubator.com/programs/data-science-fellowship/#apply


Task: Analyze the connections between being a just company and market returns. Companies are anonymized and data on the top-half of scoring companies are provided.


  • Which of the JUST Capital drivers and components, if any, are factors of alpha, particularly over different periods of time?
  • What are the characteristics of different baskets of JUST Companies, including the JUST 100 companies. Be creative.
  • Can returns alone be used to predict a company’s JUST Score? What other financial or extra-financial data would you need for such an analysis?



Task: Analyze company impacts on localized health outcomes around the U.S., using JUST Capital geolocated company operations per county and aggregate macro county indicators per county. FIPS Code is the geographic key, and is a concatenation of state and county codes. Company presence is indicated by the field Weight1.


  • Can JUST Capital data on corporate behavior, be linked to population-wide performance on measures of community health?
  • What is the relationship between county health, corporate performance and the issues important to the American public?



Task: Explore the relationship between company presence, JUST performance data, and economic and inequality outcomes per county, using JUST Capital geolocated data. FIPS Code is the geographic key, and is a concatenation of state and county codes. Company presence is indicated by the field Weight1.


  • Can JUST Capital data on corporate behavior, on the issues important to the American public, be linked to population-wide measures of economic inequality?



Task: From a corporation’s perspective, what actions can one take to have the greatest impact on JUST Score, Rank and Inclusion in the JUST 100.


  • What are the top three components a company should improve upon, in each industry, to have the greatest impact on their JUST ranking
  • By industry, what factors drive the differences between companies?


If you have any questions about the datasets listed above, feel free to send any questions to the team at JUST Capital:  data@justcapital.com. 

Related Blog Posts

Moving From Mechanical Engineering to Data Science

Moving From Mechanical Engineering to Data Science

Mechanical engineering and data science may appear vastly different on the surface. Mechanical engineers create physical machines, while data scientists deal with abstract concepts like algorithms and machine learning. Nonetheless, transitioning from mechanical engineering to data science is a feasible path, as explained in this blog.

Read More »
Data Engineering Project

What Does a Data Engineering Project Look Like?

It’s time to talk about the different data engineering projects you might work on as you enter the exciting world of data. You can add these projects to your portfolio and show the best ones to future employers. Remember, the world’s most successful engineers all started where you are now.

Read More »
open ai

AI Prompt Examples for Data Scientists to Use in 2023

Artificial intelligence (AI) isn’t going to steal your data scientist job! Instead, AI tools like ChatGPT can automate some of the more mundane tasks in your future career, saving you time and energy. To make life easier, here are some data science prompts to get you started.

Read More »