Blog

Posted on

Agentic AI: Can an AI Agent Clean Up the Hard Drive?

I’m probably not the only person who has a folder on their hard drive that should be cleaned up at some point. Mine happens to be called “Aufräumen” (Clean Up), and whenever I manage not just to keep filling it but actually want to clean it up, I’m overcome by a leaden fatigue after 2-3 files.

Anthropic’s Claude offers the possibility to connect a Large Language Model with external software through the Model Context Protocol. This means the LLM is no longer “just” limited to text output, but can make decisions or even execute actions. Claude already comes with some integrations, for example the ability to access the local file system (at the very bottom of the screenshot).

Claude integrations screenshot

My prompt: “Can you please look at my ‘Aufräumen’ folder on the desktop and see how the files there could be sensibly organized?”

First, Claude got an overview of the files in the folder. With more than 600 files, Claude needed two attempts. In doing so, Claude only examined the file names, although it would have been possible to open at least some of the files. However, that would have taken even longer. Claude then came up with a proposal in which my files were divided into 12 categories. These made a lot of sense, I only gave Claude one note before the AI cheerfully started sorting my data:

Folder structure screenshot

Just for sorting the 600 files, nearly 4 hours were necessary, partly with longer breaks because my usage limit was exhausted and I had to wait until I could use Claude again. This waiting time is not included in the 4 hours. But even so, Claude needed breaks again and again, sometimes the server was unreachable, then a context window was full and I had to type the prompt again in a new chat, or a “Continue” button appeared that had to be pressed. The computer actually got hot, Claude required a lot of power, but really needed a lot of time for each file. Sometimes it looked like this:

Claude working screenshot

For this to work at all and to avoid having to approve the action for each individual file, Claude needs approval for each action category. You should only do this if you also have a backup of your own files.

Did it work? A clear “partially”. Not all documents were correctly categorized. This is naturally also due to the fact that files were only categorized by their names. But it’s definitely a good pre-sorting, and in that time I probably would have fallen asleep several times out of self-defense. So it was worth it, even if the result isn’t perfect yet.

In the next step, I will build such a system with a locally installed LLM that also opens and reads files to sort them correctly.

Posted on

Which Visualization for Which Data?

Communicating data, information, and the insights derived from them is a key skill. Data visualizations should help the audience grasp concepts more quickly, making it essential to choose the type of visualization that conveys the message most effectively. Even though Microsoft Excel might suggest a pie chart, it’s often not the best option, as you can see on the left!

At university and in my job, I constantly work with data visualizations. To save everyone’s nerves, I’ve created a handy overview, inspired by the work of A. Abela:

The overview is continuously updated by me. If you’re interested, feel free to sign up for my newsletter and get instant access to the overview (plus a monthly update).

Posted on

Row Names in R

Some datasets in R use row names, such as the built-in mtcars dataset. While convenient, row names can be suboptimal when sorting data, for instance, by car brands:

To convert row names into a column using the Tidyverse, the rownames_to_column() function is used:

library(tidyverse)

# mtcars laden und die Reihenamen in eine Spalte verschieben
mtcars_tidy <- mtcars %>%
  rownames_to_column(var = "car_name")

And this is the result:

Posted on

estateguru: High fees if you don’t invest

Estateguru announced this year that they charge a €10 fee for an inactive account, and that’s per month! On the price list, it looks like this:

Funds held on your Lemonway account can be used solely for your transactions on the Estateguru platform. As it is a special purpose account, it should not be used for depositing funds without the intention to invest. As inactive accounts create cost to Estateguru, an “inactive account fee” is charged from users who have deposited funds in their accounts but who have not made any new investments on the Primary or on the Secondary market for the last 12 months. Starting in April 2023, the “inactive account fee” was increased to 10 EUR per month for the first year following the 12 month period of inactivity, and will increase to 50 EUR per month thereafter. The fee will be applied monthly if there is a positive balance on the user’s account. If the user makes an investment, whether on the Primary or Secondary market, the account status will be switched to active again and no further fee applies.

I’m probably not the only one trying to gradually withdraw my money, as the majority of my investment has now defaulted.

To be fair, I should mention that I have already withdrawn half of the money I had previously invested. Apparently, I’ve now reached a year without investment, as €10 has also been deducted from my account. Not great. I had tried to activate an automated investment strategy that kicks in once the account balance reaches €500, so I could at least “rescue” some of my money from time to time, but apparently, that didn’t work. This is certainly one way to force your customers into something.

For me, this means I’ll have to reluctantly make one investment per year and then gradually withdraw my money. It will take a bit longer, but so be it. I can definitely no longer recommend Estateguru.

Posted on

Visualizing overlaps of ETFs in an UpSet diagram

Today, two topics I find particularly exciting come together: data analysis and visualization, and finance. Choosing the right ETFs is a topic that fills countless web pages and financial magazine articles. However, it’s equally fascinating to explore the overlaps between ETFs. Previously, I compared the Vanguard FTSE All-World High Dividend Yield UCITS ETF USD Distributing (ISIN: IE00B8GKDB10) and the iShares STOXX Global Select Dividend 100 UCITS (ISIN: DE000A0F5UH1). I also analyzed the performance of these two alongside the VanEck Morningstar Developed Markets Dividend Leaders ETF (NL0011683594) and an MSCI World ETF (IE00B4L5Y983).

The holdings included in an ETF can be downloaded from the respective provider’s website; I performed this download on October 5. The data requires significant transformation before it can be compared. My R-based notebook detailing this process can be found [here]. For the visualization, I chose an UpSet diagram, a relatively new type of visualization that I’ve used in a paper and another project. While Venn diagrams are commonly used for visualizing overlaps between datasets, they become unwieldy with more than 3 or 4 datasets. This challenge is clearly illustrated in examples like this:

The size of the circles, for example, does not necessarily reflect the size of the datasets. An UpSet diagram is entirely different:

Yes, it takes a bit of effort, but it shows much more clearly how the datasets relate to one another. On the far left, we see the size of the datasets, with the Vanguard FTSE All-World High Dividend Yield having the most holdings—over 2,000. On the right-hand side, we see the overlaps. The point at the very bottom beneath the tallest vertical bar indicates that the Vanguard FTSE […] has 1,376 stocks that no other ETF includes. Similarly, the iShares Core MSCI World has 757 titles that no other ETF contains. In the third column, we see that these two ETFs share 486 titles that the other two ETFs do not include. I find that quite fascinating. For example, I wouldn’t have thought that the Vanguard contains so many stocks that the MSCI World does not.

The VanEck allegedly has one stock that no other ETF contains, but that’s not accurate; that entry was just cash. Otherwise, 81 of its 100 titles are also included in the MSCI World. All of its titles are included in the Vanguard.

It would now be interesting to see how the weightings align. However, that’s an additional dimension that would likely be difficult to represent in an UpSet diagram. Still, it’s necessary to take a closer look at this because the overlaps might result in unintended overweighting of certain stocks. That would be a topic for the next blog post.

Posted on

Dividend Strategies: Missed Opportunities?

Disclaimer: This is not financial advice or a recommendation!

The article “When Chasing More Dividends Leaves You With Less“ from the Wall Street Journal by Jason Zweig (who, by the way, wrote the commentary for The Intelligent Investor) sheds light on the appeal and associated risks of dividend strategies. Investors who focus on high dividend yields often hope for a steady income stream, especially in times of low interest rates. However, as the article points out, chasing high dividends can ultimately reduce long-term returns. The problem arises when investors blindly flock to funds that offer exceptionally high dividend yields.

Continue reading “Dividend Strategies: Missed Opportunities?”
Posted on

Export from ING depot: CSV is not the same as CSV

Depot student Dominik has already provided a good overview of how to export data from the ING depot via the ExtraETF workaround. However, not every tool can handle the CSV export properly. For example, DivvyDiary immediately recognized the relevant columns, but the balances didn’t match. The reason for this is that CSV files can vary significantly, as can the data within them. Sometimes, columns aren’t separated by a comma but by a semicolon. And while the difference between 1,000.00 and 1.000,00 might seem minor to us, for DivvyDiary, a 1000 turned into a 1 because the thousands separator was treated as a decimal point.

The solution: As much as I dislike working with Excel, if you open the CSV file in Excel and then save it again as a CSV, even DivvyDiary (and many other tools) can handle it.

Posted on

The advantage of ETFs with domicile in Ireland… sometimes.

Disclaimer: This is not financial advice! No warranty.

When selecting ETFs, various factors come into play, including tax considerations. In the last article, we discussed what partial exemption means. However, the tax differences between ETFs with different domiciles and their holdings in US stocks are also interesting. This article focuses on two specific and popular ETFs, and even though both contain US stocks, that doesn’t necessarily mean that the ETF domiciled in Ireland will deliver higher returns.

Continue reading “The advantage of ETFs with domicile in Ireland… sometimes.”
Posted on

Partial Exemption and Taxation of ETFs: What Does That Mean?

Disclaimer: This is not financial advice, all information is provided without warranty!

Introduction

Investments in ETFs (Exchange Traded Funds) are highly popular among investors due to their diversification, low costs, and ease of use. There are two main types of ETFs: distributing ETFs, which pay income directly to investors, and accumulating ETFs, which automatically reinvest income. However, the taxation of these earnings can be complex, particularly due to the partial exemption and the pre-tax lump sum. This article explains how partial exemption works and how accumulating ETFs are taxed in Germany.

Continue reading “Partial Exemption and Taxation of ETFs: What Does That Mean?”