Better Feature Engineering in 10 Lines of Code

Welcome to Weekly Roundup #4 at ForecastOS! We're glad to have you here, following our journey :)

This newsletter is split into three sections: 1) thoughts / musings relevant to ForecastOS, 2) what we worked on last week, and 3) what's coming next.

1. Thoughts / Musings

Better Feature Engineering in 10 Lines of Code

At ForecastOS, we're building a unified AI management (AIM) platform. But what does that mean?

It means making forecasts (and associated features, datasets, and backtests) easier to understand, audit, and manage through our UI that ties everything together:

... But it also means making forecasting inputs - datasets and features - easier to find and consume.

As such, in the coming days / weeks, we will be launching an open-source (PyPI) package and associated API that allows anyone to easily consume features and datasets - through ForecastOS - in less than 10 lines of code:

import forecastos as fc

feature_df = fc.features.read(
    'provider': 'forecastos',
    'package': 'us_financials',
    'features': ['revenue', 'ebit', 'operating_cf', 'net_debt'],
    'api_key': KEY
)

Concurrently, we will be releasing our +10MM row US financials dataset (and associated features) for +1,000 publicly traded stocks. It will be available for free, through our platform, ForecastOS.

Stay tuned!

2. Work: What Got Done

ForecastOS is a new startup. As such, we try to spend 100% of our time either building or selling. We log that effort here.

This past week, as it pertains to selling, we:

• Continued the outreach process for our unified AI management (AIM) platform; if you know anyone we should talk to, please let us know! We have capacity to onboard 1 additional client in Q4 2023

This past week, as it pertains to building, we:

• Iterated on our backtesting functionality with our first quant hedge fund client; reported results are now exactly as desired
• Hacked with Delphia at their corporate retreat in Quebec; we created a +10MM row US financials dataset for +1,000 publicly traded stocks

3. Work: What's Coming Next

It's important to keep velocity high. We keep ourselves accountable by sharing what we hope to finish over the next week.

This week we will:

• Continue outreach for our unified AI management (AIM) platform
• Build, and prepare to deploy, our open-source (PyPI) package and associated API for consuming features and datasets through ForecastOS in less than 10 lines of code
• Add advanced reporting functionality for our first quant hedge fund client
• Start planning our first (financial) forecasting competition

Until next week!