Friday check-in... how did you spend your day? ☕️✨
Anonymous Poll
33%
💻 Just quietly getting through my tasks.
11%
☕️ Enjoying a peaceful day away from the screen.
0%
🔋 Taking a deep breath and recharging for the weekend.
33%
😁 Seeing Simri's message on her channel
22%
🤷 Just doing nothing.
Forwarded from Lid's Verse (Lidiya)
The world is small place for real🤯 Some one you know knows some one. By this rate i think i might know someone who have close contact with Elon musk
@lidsverse
@lidsverse
How was your weekend, fams? 🌟 Did you take enough break to start the new week with good energy? 🔥🔥 Or did you just spend the weekend with grinding? 💪 Let us know! ☺️☺️
🥰2
🔥3👍2
Simret.exe
🔥 #DAY1 on the portfolio optimization project Today I focused on understanding the project before touching any code, and honestly, a lot of new finance concepts hit me at once🤕😁😁but I try to manage it. What I Have done and learn today: Pulled historical…
#ProjectUpdate
I got so focused on this project (and honestly surprised by how much there was to learn 😅) that I forgot to post updates. I was busy learning new finance terms and trying to finish before the deadline.
It was a great experience, but it taught me one important thing: fintech is not something you can learn quickly. It takes a lot of reading, practice, and patience because some concepts take time to understand.
What I found difficult (but finally understood):
📉 Stationary vs. non-stationary data
⚠️ VaR & Sharpe Ratio (understanding risk and reward)
🔮 Confidence intervals why long-term predictions are much less certain than short-term ones
What I built:
📊 Cleaned and analyzed real stock data (TSLA, BND, SPY)
🤖 Compared ARIMA and LSTM LSTM was about 3× more accurate
📈 Predicted TSLA stock prices for the next 12 months with uncertainty ranges
⚖️ Built an optimized investment portfolio using Modern Portfolio Theory
🧪 Backtested it against a simple benchmark to see if the strategy could actually outperform the market.
Biggest lesson:
A model that makes good predictions is not always a strategy that works in the real world. In fintech, knowing when not to trust a model is just as important as knowing how to build one.
Learning these things was challenging, but that's what real learning looks like. 💪
I got so focused on this project (and honestly surprised by how much there was to learn 😅) that I forgot to post updates. I was busy learning new finance terms and trying to finish before the deadline.
It was a great experience, but it taught me one important thing: fintech is not something you can learn quickly. It takes a lot of reading, practice, and patience because some concepts take time to understand.
What I found difficult (but finally understood):
📉 Stationary vs. non-stationary data
⚠️ VaR & Sharpe Ratio (understanding risk and reward)
🔮 Confidence intervals why long-term predictions are much less certain than short-term ones
What I built:
📊 Cleaned and analyzed real stock data (TSLA, BND, SPY)
🤖 Compared ARIMA and LSTM LSTM was about 3× more accurate
📈 Predicted TSLA stock prices for the next 12 months with uncertainty ranges
⚖️ Built an optimized investment portfolio using Modern Portfolio Theory
🧪 Backtested it against a simple benchmark to see if the strategy could actually outperform the market.
Biggest lesson:
A model that makes good predictions is not always a strategy that works in the real world. In fintech, knowing when not to trust a model is just as important as knowing how to build one.
Learning these things was challenging, but that's what real learning looks like. 💪
👏5
Hustle like your life depends on it
1 right move can change your life!
Keep moving your future self will thank you 🤝🤝🫡
#simruthoughts
1 right move can change your life!
Keep moving your future self will thank you 🤝🤝🫡
#simruthoughts
🔥3
Forwarded from AI and Machine Learning
📊 Large Language Models are AI systems trained on vast text data to understand and generate human-like language.
🧬 Built on transformer architecture, they predict the next word using patterns in grammar, context, and knowledge.
⚡️ From writing emails to coding and reasoning, they power tools like chatbots and assistants.
🔥 Flaws like bias exist, but they’re reshaping how machines think.
Language is the new code.
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
Forwarded from DOT_RUTH (Ruth Abiti)
I deleted the channel...
Then realized I had nowhere to randomly overshare my thought.
So... dot_ruth is back :)
Then realized I had nowhere to randomly overshare my thought.
So... dot_ruth is back :)
Forwarded from Beka (Beka)
Better Auth is joining Vercel!
Thank you everyone who has been part of this journey in so many different ways 🙏
More to come! Excited for what’s ahead ❤️
Thank you everyone who has been part of this journey in so many different ways 🙏
More to come! Excited for what’s ahead ❤️
❤1👍1🙏1
When you begin something, it often feels impossible and out of reach especially in the ML and ai field. But that's part of growth. Let's document the journey so we can look back and see how much we've grown.
Take some rest. We'll restart tomorrow.
Good night, fams. 🌙✨
Take some rest. We'll restart tomorrow.
Good night, fams. 🌙✨
❤2👍1