Capstone – Project

Audit Operations and Quality Control Processes. Develop Marketing ROI Reports

A Collaboration Between

Project Synopsis

Company Overview

Metaculus is a global forecasting platform that statistically aggregates and algorithmically optimizes the predictions of a community of thousands of forecasters. The Metaculus Platform has an established track record predicting key advances in science and technology.

 

Project Description

Metaculus wants to better serve and understand the existing Metaculus user base across a variety of dimensions, such as accuracy, experience, thematic interest, level of participation, discovery and onboarding pathway, and so on. Candidates will also design new statistical tools and views to deliver insights to our forecasting community.

Project Topics

Company Information

CompanyMetaculus
HQSanta Cruz, CA
RevenueUnlisted
EmployeesUnlisted
StageHigh-Growth Startup
Hiring PotentialN/A
Website

Company Overview

Metaculus is a community forecasting platform that delivers ML-optimized collective intelligence on topics of global importance. The platform brings together a global reasoning community, and keeps score for these thousands of forecasters via explicit, standardized track records. Built on data, it generates scalable ensemble forecasts while delivering consistent feedback on the quality of the reasoning and analysis of its participants. The collective intelligence generated by Metaculus connects rigorous modeling and the scientific method to complex real-world challenges, thereby improving decision-making and fostering transparency and accountability in the public domain. Its open access ensemble forecasts provide a sense-making utility for hundreds of thousands of readers, and are trusted by the scientific community, government agencies, effective charities, and the Fortune 500.

Experiential Learning Program Details

SchoolAdelphi University
Engagement FormatCapstone - Small Team Consulting Project - Students work in consulting teams of 3-5 directly with faculty and client liaisons on developing real solutions to real-world challenges.
CourseAdelphi University’s Statistical Consulting Practicum- Spring 2020
Level
  • All Undergraduate
  • Advanced Undergraduate
  • All Graduate
Students Enrolled6
Meeting Day & TimeTBD
Student Time Commitment4-7 Hours Per Week
Company Time Commitment2 Hours
Duration12.86 Weeks

Program Timeline

Touchpoints & Assignments Due Date Type
Official Project Kickoff

Official Project Kickoff

We'll web conference company senior leadership into class to introduce the company, meet the students, and discuss the project goals.
January 31st, 2020 Event na
Final Presentations Final Presentations
Students will present final insights to the company's senior leadership. Please upload the final deliverables.
April 30th, 2020 Submission Required submission-required

Key Project Milestones

  • January 31, 2020 - Conduct user analysis

    Activities:
    1. Correlate user behavior across internal Metaculus data logs, and
    Google Analytics and other data sources, in order to build a holistic and
    rich user model for Metaculus.
    2. Utilize user model to identify groups of user personas, including Best
    Forecasters, Most Active, Veterans, Newcomers, Political Forecasters,
    Science Forecasters, Forecast Readers, etc.

    Suggested Deliverable:

    Metaculus User Model and Metaculus User Personas Report

  • April 30, 2020 - Statistics Swiss Army Knife for Forecasting

    (please note that the milestone date indicated above is not accurate; a placeholder only)
    Activities:
    1. Understand how the existing graphs for the Metaculus Track Record
    page and user track records are generated – Brier score and log scores
    for accuracy, calibration plots.
    2. Identify other interesting statistical analyses that help the Metaculus
    forecasting community measure its accuracy, individually and in
    aggregate. For instance, identifying the most accurate forecasts
    when they are among the first forecasts made, identifying correlations
    between updates in forecasts across the platform, visualizing the
    transformation of an aggregate forecast over time, and so on.
    3. Develop a “Stats Swiss Army Knife” package, in R or Python, that
    enables these additional views and analyses.

    Suggested Deliverable:

    Stats Swiss Army Knife Package enabling additional individual and aggregate
    forecasting analysis

Project Resources

There are no resources currently available

Industry Mentors

There are currently no supervisors assigned.

Academic Mentors

There are currently no supervisors assigned.

Assigned Students

There are currently no students assigned.