Master's Thesis topics in quantitative finance?

[IntoDarkness]

you can do a term structure model for SOFR and use it to price some SOFR indexed MBS with monte carlo

 

[ZFL]

you can do a term structure model for SOFR and use it to price some SOFR indexed MBS with monte carlo

(y) this sounds interesting to me.

 

[rajanS]

There are too many papers online. You can just replicate one of them. I’m currently replicating “factor mimicking portfolios” you can ssrn that

 

[Krutarth Satoskar]

you can do a term structure model for SOFR and use it to price some SOFR indexed MBS with monte carlo

This seems interesting to me. Can you please elaborate more on this?

 

[Daniel Duffy]

Machine Learning (ML) in finance is becoming popular.

 

[Krutarth Satoskar]

Machine Learning (ML) in finance is becoming popular.

Can you please suggest some topics?

 

[Daniel Duffy]

Can you please suggest some topics?

Sure
ML and computational finance is also a hot topic and could be a good source.

Two very good theses here 1) ML for SABR, 2) computing option sensitivities.

https://www.datasim.nl/blogs/26/msc-theses-on-machine-learning-and-computational-finance

 

[Krutarth Satoskar]

Sure
ML and computational finance is also a hot topic and could be a good source.

Two very good theses here 1) ML for SABR, 2) computing option sensitivities.

https://www.datasim.nl/blogs/26/msc-theses-on-machine-learning-and-computational-finance

Calibrating the SABR model using ML with computational efficiency seems a very good problem

 

[Aber]

Calibrating the SABR model using ML with computational efficiency seems a very good problem

An Artificial Neural Network Representation of the SABR Stochastic Volatility Model

In this article, the Universal Approximation Theorem of Artificial Neural Networks (ANNs) is applied to the SABR stochastic volatility model in order to constru

papers.ssrn.com

I used This papir in my theiss. I Will definitely recommend this topic

 

[Daniel Duffy]

An Artificial Neural Network Representation of the SABR Stochastic Volatility Model

In this article, the Universal Approximation Theorem of Artificial Neural Networks (ANNs) is applied to the SABR stochastic volatility model in order to constru

papers.ssrn.com

I used This papir in my theiss. I Will definitely recommend this topic

Is your thesis public domain? I have a number of questions regarding McGhee's that I was unable to get an answer to.

 

[Krutarth Satoskar]

Thank you for the link. I will surely look into it. Can somebody please tell me where I can read about the pricing of these SOFR indexed MBS? This seems to be a new domain with much less literature available.

 

[lolalin]

you can do a term structure model for SOFR and use it to price some SOFR indexed MBS with monte carlo

Do anyone have a similar idea but in the equity derivatives world?

 

[Daniel Duffy]

An Artificial Neural Network Representation of the SABR Stochastic Volatility Model

In this article, the Universal Approximation Theorem of Artificial Neural Networks (ANNs) is applied to the SABR stochastic volatility model in order to constru

papers.ssrn.com

I used This papir in my theiss. I Will definitely recommend this topic

Are the results 'interpretible'?

Interpretability in deep learning for finance: a case study for the Heston model

Deep learning is a powerful tool whose applications in quantitative finance are growing every day. Yet, artificial neural networks behave as black boxes and thi

papers.ssrn.com

Something auditors and regulators like.

 

[Drumpfy]

I'm doing some math-heavy CS research. Like the math behind various learning algorithms, some of which are popular in finance. I am trying to steer it towards quant-ish stuff but it's the best I can do. I'm doing an MSCS as opposed to an MFE because of better job opportunities (My goal is to be a quant, but I'd rather be an engineer than an analyst if that doesn't work out)

 

[lolalin]

Are the results 'interpretible'?

Interpretability in deep learning for finance: a case study for the Heston model

Deep learning is a powerful tool whose applications in quantitative finance are growing every day. Yet, artificial neural networks behave as black boxes and thi

papers.ssrn.com

Something auditors and regulators like.

Thanks Dr. Duffy for your ideas

 

[Daniel Duffy]

Thanks Dr. Duffy for your ideas

You're welcome. On www.datasim.nl (BLOGS) there are 3 recent and super-modern theses to be found.

 

[lolalin]

As I'm still brainstorming ideas, I came up with a random idea to minimize hedging error with stochastic/normal gradient descent. Does this even make sense?

 

[lolalin]

Are the results 'interpretible'?

Interpretability in deep learning for finance: a case study for the Heston model

Deep learning is a powerful tool whose applications in quantitative finance are growing every day. Yet, artificial neural networks behave as black boxes and thi

papers.ssrn.com

Something auditors and regulators like.

Just a quick Q. Dr. Duffy, would with regards to the first one (Interpretability of ANN Representation of SABR) do you think this would be something Banks/HFs would find useful/interesting? I know that I should do something I personally want to do, but I also want to find something which would also interest potential employers

 

[Daniel Duffy]

Just a quick Q. Dr. Duffy, would with regards to the first one (Interpretability of ANN Representation of SABR) do you think this would be something Banks/HFs would find useful/interesting? I know that I should do something I personally want to do, but I also want to find something which would also interest potential employers

I am not an employer but my feeling is if you know this modern stuff it proves you are flexible which employers like.. Especially new startups, maybe.
Good luck!

I assume you have a supervisor whom you can chat with for some topics as well.