As I discussed in my 2025 Q2 Efficiency assessment, my central investing device is now a dynamic watchlist that prioritizes Corporations based mostly on High quality, Valuation and Momentum.
I’ve already mentioned my preliminary strategy to momentum the final time.
Now the way to strategy the standard of an organization in an environment friendly manner ?
The primary subject right here is that I won’t be able to do a “full stack” evaluation for every firm I come throughout. However I wish to have at the least a fast “place to begin” which I may use to resolve if it is sensible to dig deeper or not.
I outlined 10 standards that give me a primary perception on how an organization may match to my “Beuteschama” or not. If I’d wish to examine these standards manually, I would want to make use of a number of sources, equivalent to TIKR, some inventory web sites, the businesses’’s IR web site and the annual and quarterly studies. A course of that on common takes me at the least 60-90 minutes to get to a conclusion.
So I made a decision to check out LLMs as a way to “outsource” this primary step screening and scoring.
I name this the “10 Issue Mannequin”. One comment: After I say fascinating to me, because of this in precept I’m in search of boring, household/administration managed corporations which can be taking part in in comparatively engaging markets, rising over the long run and are conservatively financed.
That is engaging for me as it fits my funding type and danger desire. Different traders might need very totally different standards. I’ve not backtested these standards in any manner, I simply assume that corporations that rating nicely will do nicely over the mid- to long run.
At this early stage within the funding course of, the mannequin additionally consists of momentum, each, inventory value and basic momentum to get a primary glimpse how the corporate is doing on this regard.
When an organization is fascinating sufficient, I’ll attempt to substantiate the elements by way of extra evaluation in a second step earlier than I then add it to my “Prime 100 watchlist” (or not).
The ten elements (in no explicit order)
- Shareholder construction
I do like corporations which have at the least one important (or a bunch of shareholders, ideally a household) that ideally permit the corporate to make use of and execute a long run technique. Ideally, Administration itself is a part of that Group. As a threshold, I exploit 25% of voting rights.
- Working margin
Right here I exploit simplistically a threshold of 10% EBIT margin within the final FY. I’m absolutely conscious that sure enterprise fashions have larger or decrease basic working margins (COSTCO). However as I discussed earlier than: That is only a first step.
- Return on Fairness
12,5% is the hurdle which I contemplate to be an honest ROE. In fact, that is additionally a operate of leverage, however at this stage I wish to maintain issues easy.
- Long run progress
Right here, I outlined a threshold of 6% CAGR for the EPS over the latest 10 years or, if not out there, 5 years. Why 6% ? As a result of that is barely larger than nominal GDP over the long run.
- Web Debt
A web Debt to EBITDA ration of under 1 offers us 1, every little thing else is 0.
- Cyclicality
This issue requires extra judgement. I both use the overall sector or assume if the corporate has a really low beta that it isn’t very cyclical. Non-cyclical is nice and a rating of 1.
- EPS Momentum
This one checks if within the final out there monetary reporting interval, EPS has gone up. If sure, then 1, in any other case 0. It is a very crude proxy for basic momentum
- Capital allocation high quality
That is as soon as once more a standards, the place the mannequin wants to evaluate info. Within the immediate I give 7 examples of which at the least 5 needs to be fulfilled to get to a rating of 1. I additionally give the LLM some KO standards.
- Market place & Market attractiveness
Right here, I boiled it all the way down to market progress, diversification throughout international locations and prime 3 place in a market. I had extra advanced definitions however they didn’t work nicely.
- 6 and 12 month value momentum
A fast examine to have a look at inventory value momentum. I exploit easy 6 and 12 month value efficiency. If each are constructive, the rating is one.
Remaining rating:
On the finish of the train, the LLM ought to then add the person scores with a max of 10. I additionally ask for some KPIs (Market cap, P/E and many others.) , info on administration, the most recent information, a inventory chart and a strengths and weaknesses abstract.
The present model of the immediate is embedded right here:
https://drive.google.com/file/d/1ZMIf7Nh__6frI8nsyWtcTZOaZfaxO_RF/view?usp=sharing
I’d be very happy to obtain strategies for enhancements and change “immediate secrets and techniques” 😉
Basic impression & Comparability of various AI fashions.
Some remarks upfront: My aim is right here to get a fast overview with out requiring an excessive amount of effort and time (no uploads and many others.). For this train I used ChatGPT 5 Professional, Gemini 2.5 professional, Claude Professional and Mistral & Perplexity with the free variations.
Listed here are some observations:
- outcomes for a similar immediate can change considerably from at some point to a different and even one chat to a different
- Inside a chat, outcomes are inclined to worsen if you immediate just a few instances. It’s higher to create a brand new chat each time.
- Additionally the output codecs can change from immediate to immediate for no explicit purpose.
- For extra obscure corporations, the variation within the outcomes is far larger. One of many examples that I’ve within the appendix is eurokai which acquired scores between 5 and 9 out of 10.
- Typically, the fashions should not capable of appropriately add up the scores per class. So that you get 6 instances a rating of 1 and the whole rating is 5.
- Regardless of profitable the Math-Olympics, calculating a ten yr CAGR from two EPS values appears to be actually tough for all of the fashions.
- The fashions use very totally different sources for market information with a really extensive number of high quality
- The “deep analysis” modes don’t at all times produce higher outcomes. Typically it will get worse. For my function, the deep analysis modes take too lengthy in any case.
- Solely Mistral was capable of embed inventory value charts
- Usually, the outcomes are getting higher for those who ask the mannequin to only do it once more. Which is kind of annoying
- You can too get totally different outcomes for those who immediate the identical factor in two totally different languages (translation supplied by ChatGPT as an illustration)
- It makes most sense to begin with corporations you already know nicely as a way to choose the place every LLM has strengths and weaknesses.
- In case you make the standards too sophisticated, the outcomes typically worsen
- I attempted to ask the LLMs to outline standards themselves, however they typically didn’t work all that nicely
On the finish of the day, counting on one mannequin, particularly for smaller corporations is kind of hazardous, you should take a look at at the least at two of them. It’s at all times price to aks
Total, I’ve to say that my favourite LLM continues to be ChatGPT, though briefly, ChatGPT5 was actually unhealthy and sloppy. That is adopted by Gemini and Perplexity, which could be very quick.
Claude is enjoyable to make use of however not very correct. LeChat from Mistral continues to be Okay for a free device. I’d by no means use Grok for apparent causes.
Abstract:
Total, I’m fairly impressed how these LLMs work and enhance. I had been concerned in taking a look at Chatbot startups 6-7 years in the past and the advance by way of LLMs is solely breathtaking. Even within the weeks that I’ve been iterating on this duties, the fashions repeatedly improved, which I discover exceptional.
My “stay information Question & interpretation” job is clearly not the perfect use case, nevertheless it saves effort and time on my facet in comparison with handbook work.
As I simply use this as a place to begin for additional analysis, I can stay with the randomness within the outcomes.
To be continued…..
Bonus track: Styx – Mr. Roboto
Appendix: Examples
Instance 1: EVS Broadcast
ChatGPT 5 with the “suppose more durable” immediate to keep away from the sloppy fast and soiled end result. It took the longes with round 5 minutes.
It got here up with an 8 out of 10 rating. It truly obtained the ten yr EPS progress incorrect however determined to make use of the significantly better 5 yr charge which is one thing I’d do as nicely.
I just like the detailed evaluation of the Capital allocation chapter. The market phase was so so…
Perplexity got here to eight out of 10. Funnily sufficient, my weblog was referenced as a supply in an earlier question, however Perplexity appears to make use of totally different sources at totally different intervals of time for a similar immediate. It obtained nonetheless the EPS progress incorrect. EPS per share has elevated by ~6% per yr over 10 years and rather more over the previous 5 years.
Perplexity was actually quick.
Google Gemini customary:
Gemini 2.5. got here up with 8/10 factors. Out there attractiveness part it made one mistake: it thought of the EMEA area as one nation and due to this fact didn’t give some extent which is clearly incorrect. Apart from that the outcomes have been Okay.
Claude additionally obtained 10 yr EPS progress incorrect, however nonetheless gave it a 1. In any other case the outcomes have been fairly first rate , too. I appreciated the output format quite a bit.
Mistral obtained to a 6/10. It made just a few errors, equivalent to the ten yr EPS progress charge, capital allocation coverage and the share value efficiency. Curiously, it’s the solely Chatbot that is ready to embed share value charts.
Instance 2: Eurokai
Eurkai is clearly somewhat bit more durable than EVS, as there may be much less frequent info, much less analyst protection and many others. It is usually a extra sophisticated firm (firm construction, Pref shares et.). Eurokai’s 10 yr EPS progress is round 6,8%.
ChatGPT scored 6/10.
It obtained EPS progress incorrect. With the cyclical sensitivity, it gave a 0 regardless of acknowledging the very low beta. Capital allocation coverage may certainly be thought of a 0. Market attractiveness is one thing I’d not help as on a glance by way of foundation, greater than 50% of exercise is in a single nation.
Perplexity got here up with 9/10 factors. It obtained EPS progress incorrect and was somewhat optimistic on the capital allocation standards. It additionally dodn’t know that Tom Eckelmann is now CEO.However total the outcomes are very first rate.
Gemini 2.5. flash customary this time returned 6/10 factors, and had clearly some issued retrieving newer info. I simply opened a brand new chat after trying into EVS Broadcast and the efficiency appears to have immediately degraded and contained lots of errors
Gemini within the Deep Analysis mode obtained 7/10. Curiously it tried to calculate the ten yr EPS progress from historic EPS numbers, however ended up calculating solely a 9 yr CAGR. However it appropriately came upon, that from a market attractiveness, Eurokai is relying an excessive amount of on Germany (40%).
Claude customary got here out with 5/10. It made numerous errors, particularly with ROE and EBIT margin.
However, Claude dug out some great things on compensation and the bios of the Eckelmanns.
Claude in Analysis mode additionally got here out with 5/10, however did an error in including up the elements. It ought to have been a 6/10.That is one thing one sees in different fashions as nicely.
It got here up with some unusual stuff, like a non-existing share dilution.
Le Chat from Mistral scored 7/10. It additionally obtained the ten yr EPS progress incorrect, but additionally the dominating shareholder share. Curiously it was the one mannequin that embeds inventory charts.
10-Faktoren-Analyse: Eurokai KGaA
| 1 | Dominanter Aktionär ≥ 25 % Stimmrechte | 0 | Die Familie Eckelmann hält über die J.F. Müller & Sohn Beteiligungs GmbH 20,52 % der Stimmrechte. Kein Aktionär oder Gruppe hält ≥ 25 %. Keine staatliche Beteiligung. [Quelle: 16, 19] |
| 2 | EBIT-Marge > 10 % (letztes Geschäftsjahr) | 1 | EBIT-Marge 2024: 27,6 % (Nettogewinnmarge als Proxy, da EBIT-Marge nicht direkt angegeben, aber deutlich über 10 %). [Quelle: 23, 48] |
| 3 | Return on Fairness (ROE) > 12,5 % | 1 | ROE 2024: ca. 27,6 % (Nettogewinnmarge als Indikator, Eigenkapitalrendite nicht direkt angegeben, aber deutlich über 12,5 %). [Quelle: 23, 48] |
| 4 | EPS-Wachstum > 6 % p.a. über 10 Jahre (CAGR) | 0 | 10-Jahres-CAGR: ca. 1,8 % p.a. (Gesamtperformance +36 % über 10 Jahre). [Quelle: 55] |
| 5 | Web Debt / EBITDA < 1 | 1 | Netto-Money-Place oder sehr niedrige Verschuldung. Keine negativen Hinweise auf hohe Schulden. [Quelle: 23, 5] |
| 6 | Geringe Zyklus-Sensitivität | 1 | Containerumschlag ist infrastrukturnah und weniger konjunkturabhängig als viele andere Branchen. Beta nicht direkt verfügbar, aber Geschäftsmodell stabil. [Quelle: 38, 5] |
| 7 | EPS-Momentum (aktuelles EPS > Vorjahr) | 1 | EPS 2024: +75,8 % vs. Vorjahr. [Quelle: 23, 48] |
| 8 | Capital Allocation High quality | 1 | 5/6 Unterkriterien erfüllt: Keine Kapitalerhöhungen, stabile Dividende, disziplinierte Investitionen, ROE/ROIC stabil/steigend, keine Verwässerung. Keine Dividende bei Verlust oder über EPS. [Quelle: 23, 48, 5] |
| 9 | Marktposition & Marktattraktivität | 1 | Prime 3 im europäischen Containerumschlag, worldwide diversifiziert (Italien, Deutschland, Marokko, Portugal), strukturelles Wachstum im globalen Handel. Keine direkte AI- oder Zoll-Gefährdung. [Quelle: 38, 5, 30] |
| 10 | Kursperformance positiv (6M & 12M) | 1 | +16,43 % (6M), +41,12 % (12M). [Quelle: 57, 61] |
Gesamtscore: 7/10