Applications like robo-advisors, algorithmic trading, and personalized banking are redefining customer experiences. Additionally, AI-driven regulatory compliance and anti-money laundering efforts are enhancing security.
@cwayne42 ай бұрын
so dump your predictors in a net with a huge hidden layer and feed the final layer through a ridge regression?
@user-eh9jo9ep5r4 ай бұрын
If will be more privacy in finances and banking, financial grammar, physical security(benches near banks), impossibility to find private information, more high salaries from minimal to higher in all fields, technological security information, impossibility third parties to find out about accounts and numbers, ethical behavior of humans around world it will create much more safe environment for good quality life
@user-eh9jo9ep5r4 ай бұрын
If will be more privacy in finances and banking, financial grammar, physical security(benches near banks), impossibility to find private information, more high salaries from minimal to higher in all fields, technological security information, impossibility third parties to find out about accounts and numbers, ethical behavior of humans around world it will create much more safe environment for good quality life
@Garrick6454 ай бұрын
This video is just so indulging. Couldn't understand a few things but great
@gwpiaser4 ай бұрын
A wonderful seminar.
@sholadistinct5 ай бұрын
Nice
@Nakshatra606 ай бұрын
What a fantastically clear, easy to understand and concise introduction to Blockchain tech! For more people to watch and learn in my opinion. Thank you.
@spiritualiteislamique91366 ай бұрын
You have done a great job, explicit and rich content, continue like this.
@kilocesar7 ай бұрын
Quantitative Finance is really exhausting; many different authors, books, and articles contradict one another. Complexity is usually viewed with disapproval by the industry.
@brendanlydon52727 ай бұрын
My eyes wide open - if creed knew ML
@jameschen23087 ай бұрын
That was fire yo 🔥
@LostHopeoftheAges798 ай бұрын
Didn’t he say you are going to end up with short term debt bank runs??? That’s happened under Biden.
@Khari998 ай бұрын
This was a great lecture with very surprising results. I had always assumed that overfit large models would always be worse to use since the training data was finite. Never thought the opposite was the case. Great work.
@brhnkh4 ай бұрын
Am I missing something or is it just "ridgeless" regression with appropriate penalty (z) being really good?
@Khari994 ай бұрын
@@brhnkh From what I understand from the lecture, one of the key insights is that larger models should be able to perform better out of sample. The general problem with using ML for time series data is that they are easy to overfit due to the limited training set and feature representation. However with a diverse feature set, larger models should be able to generalize better which is intuitive to me.The reason why many experts would recommend against bigger models is because they are much easier to overfit to the training data but this may just because they were training with a small feature set that did not have many predictive outcomes. Whenever this is the case, a model will learn the dataset itself in order to achieve the reward without finding patterns that can be repeated in out of sample data.
@brhnkh4 ай бұрын
@@Khari99 Right. The last sentence is what's novel I think. The model gets better at out-of-sample data because it is appropriately penalized while being trained with very large number of parameters. Apparently, they figured it out using random matrix theory, so the heavy lifting lies there I guess.
@Khari994 ай бұрын
@@brhnkh the reward function is always the most difficult part of ML. It took me a while to figure out how to write mine for my architecture. Simply using max profit is not enough (a model could learn to buy and hold forever for instance) And neither is accuracy. (high accuracy != profitability). You have to reward it and penalize it in a similar way that you would a human based on metrics its able to achieve on a trade by trade and portfolio basis.
@maximlamoureux41294 ай бұрын
@@brhnkh I thought a definition of overfitting was when validation error starts to increase rapidly, after reaching its minimum during training, whilst training error continues to decrease. It is therefore not clear to me, why you would want a model to overfit at all, finance or not. I'm only 4 minutes into the video, perhaps he will explain it.
@emmanuelameyaw68069 ай бұрын
what do you mean by the model is explainable? Something like you can explain the coefficient of a linear regression model?
@maximlamoureux41294 ай бұрын
I'd say that if you can analyse the models output and inner workings to get an understanding of WHY it produces a given output. SHAP is such a tool. check it out.
@emmanuelameyaw97359 ай бұрын
There is time for everything. A time for simple models and a time for ML models.
@shreyajaiswal3800 Жыл бұрын
Nice discussion. However India already has very advanced interoperable digital payment system like UPI since 2016. We are also experimenting with our own CBDC this year.
@muskduh Жыл бұрын
thanks for the video.
@davi_96 Жыл бұрын
Steve Keen on DSGE models kzfaq.info/get/bejne/opeGhpmmlrzDeqM.html
Merci à Mr schmalz pour la compréhension du système d'exploitation et de l'hégémonie des groupes d' investisseurs mondiaux sur les dangers qu'ils font courir sur la stabilité des salariés et sur les peuples
@Kevin-xs8xn2 жыл бұрын
Some notes Interconnectedness of crises Rich literature on banking crises - but there’s systematic relationship between banking and currency crises Banking crises typically came after financial liberalization 125 countries, 300 banking crises = tight connection between capital market integration (open capital account) and incidences of banking crises In era of heavy regulation, relative dearth of financial crises Before, currency and banking crises were looked at in isolation But, banking crises often lead to future currency problems - feedback loops A legacy of banking crises is that governments end up with a lot of debt - takes over private debts / bank debts Banking crisis increases probability of sovereign debt crisis - but not other way around Pattern of steps -Financial liberalization -Boom in economic activity, asset prices -Slowdown / onset of banking problems -Bank crisis -Sovereign debt crisis How to engage severity of crisis - look at per/capita GDP, and number of years required to return to pre-crisis peak Most severe 100 crises, ranked - lots of triple crises (bank, currency, sovereign debt) Antecedents of financial crises -currency overvaluation - bad loans, firm over-profitability -asset price bubbles -credit boom -build up of short-term debt -decline of bank deposits / existence of bank runs -hidden debts - all kinds of nasty surprises are revealed during crises - Post crises recessions are longer and more protracted than norm Even by 2018, countries like Italy and Greece still had not returned to pre-crisis peaks (re: 2008 financial crisis) Legacy of these crises is build-up of public sector debt Advanced economies are no strangers to sovereign default
@khadim18752 жыл бұрын
very very interesting !!
@americanescu2 жыл бұрын
Yeah, let's hear a little more about economic usury from people who truly believe in it. Sublime!
@bleacherz75032 жыл бұрын
No mention of FED employees buying for personal accounts
@bleacherz75032 жыл бұрын
The explains why the FED is apprehensive about raising rates , it leads to (smart) savers moving money
@bleacherz75032 жыл бұрын
I’m in love 😻
@tomfrykman76152 жыл бұрын
Anna Stenberg
@francis-oq6fu2 жыл бұрын
The video sound is pretty good, beyond my imagination
@virnamisra16572 жыл бұрын
Q how would it be if China offered and Donald Trump's acceptance ensued of Chinese citizenship as he arose before upto 2025 25 December as USA president। for a tenure of 19-25 years। At Davos and Divorce reply awaited
@virnamisra16572 жыл бұрын
Your thoughts on X mas /Ex managers and Management's
@dienle88882 жыл бұрын
so touching for an excellent video
@conw_y2 жыл бұрын
Genius
@debpitman85932 жыл бұрын
Character In the video It's great, I like it a lot $$
@marat121119822 жыл бұрын
Thanks for putting the conference recordings online, very interesting keynotes and discussion panels. What I am puzzling about though is the remark by Rahmouni-Rousseau at the 1:14:18 time mark kzfaq.info/get/bejne/qLlkZ6yUx92XYYk.html about minimum reserve requirements for commercial banks in the Euroarea. She said: "there is no strict regulatory requirement for Euroarea banks to hold reserves; the requirement is on HQLA" and banks just prefer to hold reserves instead of hqla's. Does that mean legally there are no minimum reserve requirements?
@RobinBetorNMarak2 жыл бұрын
Standford Professor.... (y)
@GreatMan_from_East2 жыл бұрын
He is gonna get Nobel Prize one day in International Finance & banking.
@emmanuellepolitronacci94842 жыл бұрын
p0
@dnirenhephzibah70592 жыл бұрын
nvgpm vyn.fyi
@cha-vz9ls2 жыл бұрын
Please any one help me about how to estimate and use DSGE model in monetary policy
@wantenono54083 жыл бұрын
cool
@13adam1313 жыл бұрын
I am sorry but this is just a typical Swedish meeting, ”I agree”, “good point”, “more can be done” etc. We should instead focus on what you have done and what can be done. Why aren’t we measuring nationality? Anonymous applications will just favor typical Swedes since they already have an head start that will show up in the CV indirectly (via networks, societies, previous experience etc). One possible solution could be to implement a quota on nationality, gender, background etc.
@abhishekpande80953 жыл бұрын
Great joke 😀
@ahmedsameh30473 жыл бұрын
Give them more time to speak, they are cutting some important issues