Bastiaan Stücken, MSc, FRM

The evolution of negative day-ahead prices in the Netherlands.

5

Very interesting session by Yves Hilpisch last week on using re-enforcement learning for financial trading. Any data scientists in the financial industry, or trying to get into the industry, should definitely be following Yves and also reading one of his (many) books on the subject! Thanks to Open Data Science Conference (ODSC) for hosting

20

2 commentaren

Seasonal Trading and Strategic Investment in High-Revenue Companies Seasonal trading presents a unique opportunity for investors to capitalize on markets with high revenues during specific periods. These investments can sometimes result in a once-in-a-lifetime financial gain if approached strategically. For instance, during holiday seasons such as Christmas, companies like Walmart and Amazon experience multi-billion dollar revenues. Similarly, Thanksgiving and Independence Day in the United States also see significant market activity and consumer spending. For portfolio managers, incorporating seasonal investments is a key diversification strategy. In Saudi Arabia, seasonal trading is prominent during events like Eid Al-Fitr, Eid Al-Adha, the National Day, and Ramadan, among others. However, a notable difference between the Saudi and U.S. markets lies in accessibility. While U.S. markets offer a wide array of publicly traded companies, the Saudi market often features a limited number of publicly listed companies, with many businesses being family-owned or privately held. This limitation restricts investors from capitalizing on high-impact seasonal companies. To address this gap, it is essential to encourage the public listing of influential companies in Saudi Arabia. Expanding the market with more publicly traded companies would attract significant capital inflows, diversify investment options, and stimulate economic growth. Investing in seasonal trading, especially by diversifying across multiple high-revenue companies, provides a more balanced and profitable approach compared to concentrating investments in just two or three firms. Furthermore, prioritizing companies that distribute dividends—whether quarterly or semi-annually—can enhance returns and provide consistent income streams for investors. In conclusion, leveraging seasonal trends and promoting market accessibility are essential for optimizing investment opportunities, both locally and internationally. This strategy not only enhances portfolio diversification but also ensures steady, long-term financial growth.

2

Thanks to @Martin Larch and team for the great Compliance Tracker database including this last update, which is enormously helpful for research on European fiscal rules. Your correlation is fascinating and suggests to me that a lack of rule enforcement, including an overly generous interpretation of the escape rules, is one of the factors that has led to the increasingly risky current debt positions in key euro countries.

8

1 commentaar

@Christofer in stead of academic research we should look into two market forces on from the policy decision promarket,projob,proGDP downplay of Fed mind set consistent especially in 2024 election year the other market bull support Fed fighting recession new priority though ate pauses, rat cut speculation led M7 meg caps trillion dollar cash share buy back drive major indices to new high created trillions capital gain support bull market, job, GDP pull US out of 2023 recession continue into 2024 drive up record sticky inflation delay interest rate cut and possible rate hike into 2025.

2

@Christofer Inflation is the products of your central banks policy intention, and mind set, can easily control to your target though follow strict QT rate hike and QE easing rate cut, you need sacrifice belt tightening, market correction remove overheated stock housing bubble, never rely all time high housing stock bubble to pull out recession ,led runaway inflation you can easily sacrifice slowdown recession cool the inflation to target like 2008.

1

Miquel Trafí Ruiz Maurits Brinkman and I wrote a paper: "Agentic Framework for Automated Multi-Document Financial Analysis" https://lnkd.in/dqiGv5jh AIFI - Artificial Intelligence Finance Institute Captide

57

1 commentaar

Another comprehensive and complete document, a Master Thesis submitted at the University of Twente in July 2022 entitled: Inherently interpretable Machine Learning for #Probability of Default Estimation in IRB Models. The thesis was submitted in fulfillment of the requirements for the degree of Master of Science in the field of Financial Engineering and Management. In the thesis, the topic of 𝗶𝗻𝗵𝗲𝗿𝗲𝗻𝘁𝗹𝘆 𝗶𝗻𝘁𝗲𝗿𝗽𝗿𝗲𝘁𝗮𝗯𝗹𝗲 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗮𝗹𝗴𝗼𝗿𝗶𝘁𝗵𝗺𝘀 𝗳𝗼𝗿 𝘁𝗵𝗲 𝘂𝘀𝗲 𝗶𝗻 𝗶𝗻𝘁𝗲𝗿𝗻𝗮𝗹 𝗿𝗮𝘁𝗶𝗻𝗴𝘀-𝗯𝗮𝘀𝗲𝗱 𝗺𝗼𝗱𝗲𝗹𝘀 is investigated. Three different high potential models will be assessed and compared on their applicability for the use in internal ratings-based models, specifically on the probability of default component. In terms of performance, the author indicates that the 𝗟𝗠𝗧 𝗮𝗻𝗱 𝗚𝗔𝗠𝗜-𝗡𝗲𝘁 showed to 𝗼𝘂𝘁𝗽𝗲𝗿𝗳𝗼𝗿𝗺 𝘁𝗵𝗲 𝗹𝗼𝗴𝗶𝘀𝘁𝗶𝗰 𝗿𝗲𝗴𝗿𝗲𝘀𝘀𝗶𝗼𝗻 with respectively an increase of 1.29% and 2.03% in terms of area under the #ROC curve. Although the GPSR did not outperform the logistic regression in terms of performance (-1.33%), it has some other interesting qualities that can be proven to be of use in future research as demonstrated. To conclude, after the LMT as runner-up, the main competitor of the logistic regression model is the GAMI-Net, which seems to have the right balance on the interpretability-performance trade-off. This thesis is a technical document namely addressed to model risk management practitioners and experts. #modelriskmanagement #riskmanagement #IRB #machinelearning #PD #probabilityofdefault #ECL #logisticregression #LMT #GAMINET #GPSR #ML #MRM #information #futurerisk #resources #knowledge #management #GRC #algorithms #decisiontrees #datamanagement #modelselection

48

A visual comparison of 10 major banks in the Netherlands based on Total Assets, Net Income, Market Share, and ROA in 2023. (Source: thebanks.eu) #PowerBI #VisualReport #DutchBanks #TotalAsset #NetIncome #MarketShare #ROA

5

In this video, economists Wilbert van der Klaauw and Gizem Kosar highlight the breadth and depth of information collected in the Survey of Consumer Expectations (SCE) and how the large-scale dataset sheds light on U.S. consumers' perceptions of and expectations for the economy and their own financial circumstances. Check out the key findings from today's SCE release here: https://nyfed.org/3yF9afJ

47

1 commentaar

📢 New working paper! 📢 Our article "End-of-Day Reversal" is now available online 🎉! This is joint work with Guido Baltussen and Zhi Da Did you know that individual stocks often experience sharp intraday return reversals during the final 30 minutes of trading? 📊 This "end-of-day reversal" is more than just noise—it’s economically and statistically significant, setting itself apart from typical intraday market momentum. More importantly, we show that this effect is mainly driven by positive price pressure on intraday losers 📉 🔍 What’s driving this pattern? 🚱 Interestingly, it can’t be explained by liquidity needs or gamma hedging. 💡 Instead, two novel forces emerge: ‼️ Attention-induced retail purchases as investors jump in late in the day. 🩳 Short-seller risk management, where shorts close positions to mitigate overnight risks. This fascinating dynamic underscores the importance of understanding behavioral and risk management drivers in stock price movements. Whether you're a trader or an investor, the last 30 minutes might be more influential than you think. 🕒💥 Our article can be read here: https://lnkd.in/euNHvBp6 Feel free to contact me in case of questions and/or comments 😊! Erasmus School of Economics Tinbergen Institute Erasmus Research Institute of Management (ERIM) Robeco #research #academic #financial #markets

89

1 commentaar

QUICK ANALYSIS: What next for the #Mag7 given the macro shifts we have seen ❓ 👉 We noted a few weeks back in our Linkedin post that the Mag7 12 month Forward PE was 2 standard deviation *expensive* to the overall macro information set (RED CIRCLE) 🚨 Now it has swung to 2 standard deviations **cheap** to macro (GREEN CIRCLE) One can model the PE as a function of economic growth, inflation, nominal & real rates, credit spreads, energy prices, the Dollar and various other measures of investor risk aversion. The chart shows: 1️⃣ The Actual Fwd PE (white line, left scale) 2️⃣ The GAP between the Actual PE and the Macro Warranted PE in standard deviation terms Indeed, you can see this for 12,000 stocks, indices and sectors globally. This has been one enormous swing. The Fwd PE has gone from pricing in strong growth (no landing at all) to a crash landing #mag7 #apple #tesla #meta #alphabet #amazon #netflix #nvidia

22

8 commentaren

𝐍𝐨𝐭𝐢𝐜𝐞𝐚𝐛𝐥𝐞 𝐢𝐧𝐜𝐫𝐞𝐚𝐬𝐞 𝐢𝐧 𝐭𝐡𝐞 𝐦𝐞𝐝𝐢𝐚𝐧 𝐢𝐧𝐯𝐞𝐬𝐭𝐦𝐞𝐧𝐭 𝐬𝐢𝐳𝐞𝐬 𝐟𝐨𝐫 𝐬𝐞𝐞𝐝, 𝐩𝐫𝐞-𝐬𝐞𝐞𝐝 𝐚𝐧𝐝 𝐚𝐧𝐠𝐞𝐥 𝐫𝐨𝐮𝐧𝐝𝐬 𝐢𝐧 𝐭𝐡𝐞 𝐍𝐞𝐭𝐡𝐞𝐫𝐥𝐚𝐧𝐝𝐬. Triggered by comments of Tommy Hurley and Rinke Zonneveld on my post (https://lnkd.in/ds7rWpAc), I had a quick search on seed rounds in the Netherlands in recent years. 📌 There's been a noticeable increase in the median investment sizes for seed, pre-seed and angel rounds in the Netherlands. 📌 Angel investors have been contributing smaller amounts in recent years. This shift has paved the way for venture capitalists to become more prominent players in seed rounds or angels consolidate with VCs more? 📌 The total number of seed deals has declined in recent years. 📌 Combining with the analysis in my post given above, seems that we observe less promising seed stage climate in recent years in Dutch ecosystem. Also maybe early stage ventures are becoming more and more capital intensive, as Rinke Zonneveld cited? - this will be tested in another analysis later! 𝐖𝐡𝐚𝐭 𝐝𝐨 𝐲𝐨𝐮 𝐭𝐡𝐢𝐧𝐤? #vcinvestments #venturecapital #SeedInvesting

16

1 commentaar

In this article, we’ll explore how to harness Numba for common Monte Carlo tasks like basic random sampling, parallel simulation, and Markov Chain Monte Carlo (MCMC) implementations.  #statology

3

Good morning, For those interested—if any—I’m sharing a short piece of work on systemic risk forecasting (quite a topic nowadays, isn't it?) that I did with Chiara Carrara and Silvia Figini. The true origin of this work lies in the early months of my PhD. I’ll leave the link in the comments. This work is a bit more layered than the one I shared with you last time. For this reason, I’ll also leave a bullet-point guide in the comments, which presents all the intuitions and the chain of reasoning in the paper in a very intuitive way. A few preliminary notes before I share the abstract and the link in the comments: - Yes, there is survivorship bias in the data used in the empirical part. But this is one of the very rare cases where it actually worsens the results. I’ll leave it to those interested to discover why. - No, what is proposed in the work is not the most effective way of exploiting the underlying intuition, but I’ll leave that for the interested reader to explore—if there is anyone. - In the empirical analysis, you’ll see some comparisons with other systemic risk forecasting measures. Some of them are true, simple, and unknown gems. You can thank me later. I hope someone finds it useful. I also attach some equity curves - I know you guys like them. Besos. Here’s the abstract: The paper proposes an innovative indicator for systemic market risk prediction using random matrix theory to evaluate multicollinearity among deep latent factors from an autoencoder-based asset pricing model. During market turmoil, securities' correlations intensify, reducing diversification benefits. Our neural network autoencoder extracts deep latent factors that adapt dynamically to input variables and possess inherent orthogonality. This indicator, revealing temporary linear dependence among these factors, is a robust early warning signal, guiding an adaptable disinvestment strategy. Empirical analysis shows significant improvements of the investment strategy based on the indicator, both in risk indicators and risk-adjusted performance, compared to the benchmark portfolio.

81

19 commentaren

Excited to be presenting our paper "Peer Momentum" at the North America Summer Meeting (NASM) of the Econometric Society 2024 in Nashville. This is a neat collaboration with Ulas Misirli and Mihail Velikov, in which we combine my econometrics and network analysis expertise with their asset pricing expertise. Abstract: Using recent advances in network theory, we estimate the intra-industry volatility connectedness for US publicly traded companies going back to the 1920s. Our volatility connections are related to the vertical upstream/downstream potential of peer firms in the supply chain and to their technological closeness. We develop a stock-level composite centrality measure that captures multiple dimensions of a stock’s interdependence with its industry peers. Using our network and composite centrality estimates, we develop "peer momentum" trading strategies, which sort stocks on their industry peers’ past month average returns weighted by the peers’ influence in the industry. A "peripheral peer momentum" strategy that uses only peripheral stocks’ influence for weighting in the signal construction achieves an annualized Sharpe ratio of 0.65, survives a battery of robustness tests, and helps explain industry momentum. SSRN link:

40

Time Series Econometrics - Excel at the Work Place: Module 1 PDF Attached: See for yourself how accessible, easy and non-mathematical I've made time series econometrics for professionals and students across the spectrum and worldwide. Next, you can view the the video on the application of this module using Eviews by clicking on the second link below: - Course :'Application of Time Series Econometrics Using Eviews - Basic, Intermediate, and Advanced Level' - 32 Modules, Approx. 22.5 hours (self-paced). Recommendation: take at least 10-12 weeks to complete this intensive course - if interested in enrolling. Course: https://lnkd.in/gVtiKQeJ Sample - Module 1: https://lnkd.in/gJ4uhfEJ *Never use this online course (32 modules - video-based) for any kind of academic study or research. This course is strictly vocational and meant for the work place - more specifically for those who are or will be soon be working in the private/commercial/business/corporate sector in any economy (developed or emerging) across the globe. * This course provides a range of tools, techniques, and time series econometric models (and demonstrates how to use Eviews) - which one can readily apply at the work place. Further, I've pioneered such as course under the assumption that one does not have the luxury of time at the work place. One has to often work amid stringent deadlines. Therefore, I've come out with a fairly comprehensive, ready-to-use, and highly accessible course for those who wish to use time series econometrics on the job across sectors/industries/economies. * Key point: one may know how to construct highly complex models - which usually take a lot time (and often prone to various data-related problems). However, due to the imperatives (i.e. fast-paced nature) of the work place, it's important to keep in mind that one focuses on quality, rather than complexity, in analysis and modelling of 'real world economic, financial, and industry data,' and settles for 'pragmatic or smart solutions.' I've not really found cook-book solutions when working with real-world data - which often has its own unique set of challenges. My background in brief: This online course is based/predicated on my work experience (+20 years). I am a macroeconomist and econometrician and currently working in an economic and industry research firm. I've worked predominantly in London and New Delhi. Further, long years ago, I was academically trained in time series econometrics and economics in London and Belgium. I am a specialist in economic outlook (22 economies), industry, and time series econometric analysis - incorporating country, financial markets, and geopolitical assessments in my work. .#Econometrics #DataScience #ProfessionalDevelopment #EViews #Australia #UK #EU #LatinAmerica #Gulf #MiddleEast #Asia #Africa  

23

1 commentaar