Automate Excel-based credit risk model in R
- or -
Post a project like this917
$1.0k
- Posted:
- Proposals: 3
- Remote
- #3409751
- Awarded
Description
Experience Level: Expert
I need an R programmer who can automate a manual, Excel-based workflow that takes as input raw financial data and outputs a single credit score. The goal of this project is to build and operationalize an API-based pipeline that does what the incumbent process does: return a number indicating the credit worthiness of a company based on 9 financial metrics, calculated from raw financial statement data.
The API needs to accept a single alphanumeric string, representing a company, and respond with its credit score. The HTTP REST API will respond to requests from a client with a credit score in JSON format.
The credit score is a function of 9 financial metrics. After each metric is calculated it's converted to a score between 1-5 which is then multiplied by a weighting factor between 1-3. These converted values can range between 0-15. These values are then summed to produce the final credit score than ranges between 0-100.
If the value of each metric is denoted X, then each metric is calculated according to the screenshot attached, called "Metric Definitions".
Good to know:
* No predictive modeling is required.
* Reference architecture is attached.
* I have some R code already written to authorize the connection to the Codat API.
* I have documentation on every metric, examples of what the output should look like, and can vouch that Codat's API docs are high quality.
Basic Outline of Project
1. Pull financial data from Codat API
2. Clean data
3. Compute each metric
4. Persist cleaned data and metrics to Postgres table
5. Compute credit score
6. Return credit score when called through API request
7. Persist credit score in Postgres table
This should take around 15-25 hours depending on your R skills. I'm open to hearing your thoughts on scope and expected effort! Also, I'll pay an additional $500 to the person who can get this done by October 11th.
The API needs to accept a single alphanumeric string, representing a company, and respond with its credit score. The HTTP REST API will respond to requests from a client with a credit score in JSON format.
The credit score is a function of 9 financial metrics. After each metric is calculated it's converted to a score between 1-5 which is then multiplied by a weighting factor between 1-3. These converted values can range between 0-15. These values are then summed to produce the final credit score than ranges between 0-100.
If the value of each metric is denoted X, then each metric is calculated according to the screenshot attached, called "Metric Definitions".
Good to know:
* No predictive modeling is required.
* Reference architecture is attached.
* I have some R code already written to authorize the connection to the Codat API.
* I have documentation on every metric, examples of what the output should look like, and can vouch that Codat's API docs are high quality.
Basic Outline of Project
1. Pull financial data from Codat API
2. Clean data
3. Compute each metric
4. Persist cleaned data and metrics to Postgres table
5. Compute credit score
6. Return credit score when called through API request
7. Persist credit score in Postgres table
This should take around 15-25 hours depending on your R skills. I'm open to hearing your thoughts on scope and expected effort! Also, I'll pay an additional $500 to the person who can get this done by October 11th.
Brandon D.
0% (0)Projects Completed
1
Freelancers worked with
1
Projects awarded
33%
Last project
27 Oct 2021
United States
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
There are no clarification messages.
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies