Building a Semi-Discretionary Stock Screening System

Summary

The document considers turning an investor’s discretionary stock selection into a systematic screening process. Candidate inputs include institutional holdings disclosures, repurchases, insider trades, expectations, fallen-angel ratings, enterprise value relative to operating earnings, and company events such as executive departures or litigation. The question is whether an existing framework can combine these signals.

The answer suggests storing the data in a daily database and using a short script to calculate screens or rankings for delivery. It also mentions spreadsheet workflows when market-terminal data is available, and a separate platform for backtesting. The discussion remains high level: it does not specify signal definitions, data sources, handling of reporting lags, portfolio rules, or evidence that the proposed screen would outperform. These omissions matter because the listed inputs mix valuation, corporate actions, sentiment, and event information.

Key ideas

• A semi-discretionary stock process can be modeled as a screen combining several company and event inputs.
• Suggested inputs include institutional holdings, repurchases, insider activity, valuation, expectations, and corporate events.
• A daily database can support automated scoring and ranking of candidate stocks.
• Spreadsheet tools may be sufficient for screening when terminal data is available.
• Backtesting requires additional tools and does not by itself establish that the screen will be profitable.

Tags

# Building a semi-discretionary system


# Building a semi-discretionary system












I've been investing for the last 15 years in a weird Buffett/Soros way. For the last few years I've been toying with the idea of modeling myself.

I want to build a 'stock screener' that will be able to suggest stocks based on:

- 13F (like Buffett).

- Stock repurchase.

- Inside trading.

- Expectations.

- Falling angels score.

- EV / EBIT.

- Company events (ceo left, class action, ..)

Is there an existing framework that I can use to allow me to achieve this? I'm a Python programmer (dayjob)

Thanks

EDIT: I found this book- Systematic Trading: A unique new method for designing trading and investing systems that also comes with the python project. I'm reading the book, so far looks promising

## Answer by Jacques Joubert (score 2)

https://quant.stackexchange.com/a/46677

Given you have a database that stores this data daily, you could write a short python script to apply your screening and email you the daily rankings or scores.

I think you can even do this in Excell if you have a Bloomberg or TR terminal. I am pretty sure that you can.

If you want to backtest the performance of such a strategy then I think using Quantopians platform is the best and easiest way to go.

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.