Hi, I’m Anand Upadhye – a Sr. Quant with over 10+ years of experience actively trading and investing in the Financial Markets (Globally). I’ve traded all sorts of securities ranging from Fixed Income to Complex Derivatives.
Over the years I’ve been fortunate enough to make mistakes, lose money, make money, and in general be in a position where I make just enough to sustain myself and my family each month.
These days aside from investing, I mostly do freelance work for clients all over the world – building and maintaining complex financial systems (high-speed) – and I absolutely love what I do.
I’m not a millionaire, or a billionaire; neither have I made a killing trading the markets, nor do I have a huge following on Insta or YouTube or TikTok.
I’m just an average guy hustling everyday to make things happen.
That brings me to Kalki GPT
Over the years I’ve constantly strived to find some semblance of an edge when in comes to trading/investing in the financial markets – and I’ve experimented with a million permutations and combinations (I still do!) – battle tested the algorithms and data-analysis in the real-world market scenarios, constantly fine-tuning them to arrive at something that can, realistically, generate high-probability trade ideas – not perfect, but a notch above the usual “Support and Resistance”, “Moving Averages”, “RSI”, “MACD”, etc. or whatever indicators are popular amongst the kids these days.
Don’t get me wrong – those indicators do serve a purpose, a valuable one; but I feel you always need something more to supplement the analysis, so that you can make better, high-probability, investment choices.
That is where Kalki GPT comes into play. No need to change your existing system – you can use Kalki as a supplementary analysis layer that gives you an added dimension/birds-eye view of the markets (Macro and Micro environment), within the context of your existing portfolio or potential trades (LONG or SHORT).
On the backend, Kalki is a complex, multi-layered analysis engine, built on top of a stack of Algorithms, with LLM’s only being used for the sake of data interpretation and commentary, such that the analysis is presented in simple, easy to understand, human readable format – and not bunch of thetas, betas, alphas, or other jargon terms being thrown around at a Wall-street fundraiser.
So to summarize, our engine does all the data analysis, number-crunching, and heavy-lifting – passes the final results to an AI (LLM) for intepretation and commentary.
With that said, I’ll shut-up now and let our product do the talking 🙂