Investment Analysis: An AI-Powered Chatbot for Mining Investment Insights

  Рет қаралды 16,327

Purdue University Daniels School of Business

Purdue University Daniels School of Business

18 күн бұрын

Explore the power of Generative AI in revolutionizing financial analysis! This video delves into our research on automating metric extraction using advanced technologies including Large Language Models, NLP, vectorization, and RAG. Discover how we harnessed web scraping for collecting SEC filings and implemented cutting-edge NLP and vector search techniques for precise content retrieval. Learn about our innovative AI assistant-style chatbot, designed on Vertex AI, which simplifies financial queries and offers personalized insights.
Join us in uncovering the future of automated financial solutions that reduce human error and save time. Don't miss out on the transformative impact of Gen AI in finance!
Team Members:
Soham Agarwal: / soham-agarwal
Durga Madhab Dash: / durgamadhabdash
Anto Frederic Henry Mohan Dass: / anto-frederic
Chaitanya Varma Sanaboina: / chaitanya-varma-sanabo...
Sai Bheeshma Ramaraju Pagilla: / bheeshma-ramaraju
Mentors:
Matthew Lanham: / mattlanham
Ashwin Mishra: / apmishra
MS BAIM Program: business.purdue.edu/masters/p...
Make sure to LIKE this video and SUBSCRIBE to our channel to keep tabs on everything the Mitchell E. Daniels, Jr. School of Business has to offer.
Follow us on social media: purdue.university/businesssocial
To learn more about the Mitchell E. Daniels, Jr. School of Business, visit business.purdue.edu

Пікірлер: 57
@chaitanyavarma3818
@chaitanyavarma3818 11 күн бұрын
Amazing team that I worked with. Loved what we achieved!
@supriyasiddineni7606
@supriyasiddineni7606 9 күн бұрын
All the Best. Great job
@tjteja4941
@tjteja4941 14 күн бұрын
Excellent work 👏🏻
@SheelaAwat
@SheelaAwat 13 күн бұрын
Wishing the team success. All the best!
@priyareddy6285
@priyareddy6285 9 күн бұрын
great work guys
@antofrederick5116
@antofrederick5116 15 күн бұрын
Interesting! Great job gentlemen!
@richakhemka7364
@richakhemka7364 15 күн бұрын
Very nice Soham
@ayushratan6452
@ayushratan6452 9 күн бұрын
Great Job Soham and team 🎉
@leelaprasad4295
@leelaprasad4295 15 күн бұрын
Great job 👏
@taranginikrishna
@taranginikrishna 14 күн бұрын
All the best team
@user-xz6be2jw2n
@user-xz6be2jw2n 15 күн бұрын
Great job 🎉
@rajsuddamalla1586
@rajsuddamalla1586 14 күн бұрын
Good job!
@jayabhupalam8885
@jayabhupalam8885 12 күн бұрын
All the Best Soham 👍
@rajeshwarraog1690
@rajeshwarraog1690 15 күн бұрын
Very Great.🎉
@shekharagrawal4432
@shekharagrawal4432 15 күн бұрын
Great work
@saireddyvelagala4198
@saireddyvelagala4198 15 күн бұрын
Excellent innovation
@user-qh6vd8id1s
@user-qh6vd8id1s 15 күн бұрын
Excellent 👏👏👏
@SathyaRajagopal-rb9ol
@SathyaRajagopal-rb9ol 15 күн бұрын
Looks interesting!
@chakrijagarapu8883
@chakrijagarapu8883 15 күн бұрын
Good job 🎉
@akhileswar0076
@akhileswar0076 13 күн бұрын
All the very Best bro
@rupaskitchennhome984
@rupaskitchennhome984 14 күн бұрын
All the best 🎉
@rajesh2089
@rajesh2089 14 күн бұрын
All the Best,❤
@braos5130
@braos5130 14 күн бұрын
Nice one
@navodayashanker305
@navodayashanker305 15 күн бұрын
Superbbb
@arunachalamterapalli7650
@arunachalamterapalli7650 15 күн бұрын
Excellent
@ponnuruhanisha1307
@ponnuruhanisha1307 15 күн бұрын
Sohhaaaammmm 🎉🎉🎉🎉🎉 All the best Buddyyy ❤❤❤❤
@CKRao-hv9zz
@CKRao-hv9zz 15 күн бұрын
Great🎉
@RA-tt8sr
@RA-tt8sr 9 күн бұрын
👍👍
@user-cw5ey9pi4t
@user-cw5ey9pi4t 15 күн бұрын
All the best
@drvikassinghal4923
@drvikassinghal4923 15 күн бұрын
Super
@jnaneswarib3184
@jnaneswarib3184 11 күн бұрын
All the best my dear ❤
@user-bk1ob6uj6b
@user-bk1ob6uj6b 9 күн бұрын
Great Idea.. 👍
@priyareddy6285
@priyareddy6285 9 күн бұрын
yeah
@dr.swadeshsingh6589
@dr.swadeshsingh6589 15 күн бұрын
Great
@madonnchocolates3335
@madonnchocolates3335 15 күн бұрын
Great wishing Success, Success, Succes and gtoqth
@ravinderaccount4893
@ravinderaccount4893 15 күн бұрын
Keep it up
@dr.b.nagaparameshwari9423
@dr.b.nagaparameshwari9423 10 күн бұрын
👏👏
@chaitanyavarma3818
@chaitanyavarma3818 11 күн бұрын
@siarazdan4756
@siarazdan4756 15 күн бұрын
go soham!
@rajatmaestro
@rajatmaestro 15 күн бұрын
Impressive, how and when can we use this for the Indian markets?
@manojmanike9202
@manojmanike9202 10 күн бұрын
Nice work with the video! Idea Seems interesting…
@A-10goBRRRT
@A-10goBRRRT 10 күн бұрын
i agree. i am sathvik btw
@ChaitanyaSanaboina
@ChaitanyaSanaboina 11 күн бұрын
Unique solution! Much needed in today's world.
@urvishmahajan
@urvishmahajan 15 күн бұрын
That guy Agarwal in the video has a good vibe. He should play guitar or something
@krishnateja0710
@krishnateja0710 10 күн бұрын
The video is about business management not a live concert at a cafe
@johndoe-f4s
@johndoe-f4s 10 күн бұрын
so basically rudimentary web scraping and a basic api plugin. Don't use buzzwords like ai when you dont know what it means.
@sohamagarwal00
@sohamagarwal00 10 күн бұрын
If it was that simple it wouldn't have taken 6 months
@johndoe-f4s
@johndoe-f4s 10 күн бұрын
@@sohamagarwal00 yeah it shouldnt have taken 6 months
@sohamagarwal00
@sohamagarwal00 10 күн бұрын
Nice one! So basically lemme explain: - We did call APIs for the model, because building a model from scratch would have been difficult and expensive. But the issue with these base models were that they didn't perform well. models like the text-bison-32k were giving very low accuracy along with Gemini. It wasn't able to retrieve the right information. - Although we couldn't alter the model, we were able to change a lot of factors out of which the following worked for this problem statement. 1) Query Rephrasing: By transforming the query "What is the PPNE for 2018?" to "What is the Plant, Property, & Equipment value for 2018?", the model facilitates better matching in the documents where the acronym may not be explicitly used. The original text from SEC filings often does not directly match the query terms due to variations in terminology. By rephrasing the queries, we could bridge the gap between the query language and the language used in the documents, improving the effectiveness of text matching. 2) Dynamic Context Window Adjustment: The "dynamic adjustment" of the context window in the model refers to an iterative process where the model evaluates and adjusts the amount of text it considers generating accurate responses. Initially, the model retrieves a context that might typically suffice for answering a query. If this context, assessed by a character count (e.g., less than 100,000 characters), is deemed insufficient for a precise response, the model expands the window by including additional text or documents. This process continues until the context is sufficiently large, ensuring that the nuances and details necessary for accurate financial reporting are preserved in the model's responses, thereby adapting to the variable information density and relevance found in different sections of financial documents. These are about 2 out of the 7 points that we changed. Thanks so much for showing interest, id love to answer any more questions.
@johndoe-f4s
@johndoe-f4s 10 күн бұрын
@@sohamagarwal00 so other than the simple api request and parameter changes. my main concern is promoting this half assed chatbot as ai powered when in truth it is nothing but a search and query feature for SEC filings. and saying that it still produces errors is basically stating that its a really bad search and query bot no better than a simple sql library.
@sohamagarwal00
@sohamagarwal00 10 күн бұрын
My man that's not how SQL works. And also it's not just parameter changes. Why so salty 😂 who hurt you, I'll help out
@user-bk1ob6uj6b
@user-bk1ob6uj6b 9 күн бұрын
All aspirants gather here
@psp785
@psp785 10 күн бұрын
Dumb
@ramakanthagarwal5479
@ramakanthagarwal5479 15 күн бұрын
Super
@AshokKumar-vr1rr
@AshokKumar-vr1rr 15 күн бұрын
Great
Unlocking Retail Potential Using Demand Sensing Techniques
2:58
Purdue University Daniels School of Business
Рет қаралды 16 М.
DO YOU HAVE FRIENDS LIKE THIS?
00:17
dednahype
Рет қаралды 82 МЛН
3M❤️ #thankyou #shorts
00:16
ウエスP -Mr Uekusa- Wes-P
Рет қаралды 13 МЛН
Дибала против вратаря Легенды
00:33
Mr. Oleynik
Рет қаралды 5 МЛН
HOW DID HE WIN? 😱
00:33
Topper Guild
Рет қаралды 38 МЛН
What is Retrieval-Augmented Generation (RAG)?
6:36
IBM Technology
Рет қаралды 592 М.
Unlocking Document Automation with Vertex AI Platform
7:38
Google Cloud Tech
Рет қаралды 7 М.
Purdue OWL: Layering Reports - The Executive Summary 1
6:35
OWLPurdue
Рет қаралды 57 М.
Producción de Gaviones
0:20
Fence & Mesh China Supply Chain
Рет қаралды 182
Is data management the secret to generative AI?
11:36
IBM Technology
Рет қаралды 21 М.
Learn GitLab in 3 Hours | GitLab Complete Tutorial For Beginners
3:26:43
Purdue OWL: Layering Reports
8:41
OWLPurdue
Рет қаралды 12 М.
DO YOU HAVE FRIENDS LIKE THIS?
00:17
dednahype
Рет қаралды 82 МЛН