Join devRant
Do all the things like
++ or -- rants, post your own rants, comment on others' rants and build your customized dev avatar
Sign Up
Pipeless API
From the creators of devRant, Pipeless lets you power real-time personalized recommendations and activity feeds using a simple API
Learn More
Search - "forecasting"
-
Smart India Hackathon: Horrible experience
Background:- Our task was to do load forecasting for a given area. Hourly energy consumption data for past 5 years was given to us.
One government official asks the following questions:-
1. Why are you using deep learning for the project? Why are you not doing data analysis?
2. Which neural network "algorithm" you are using? He wanted to ask which model we are using, but he didn't have a single clue about Neural Networks.
3. Why are you using libraries? Why not your own code?
Here comes the biggest one,
4. Why haven't you developed your own "algorithm" (again, he meant model)? All you have done is used sone library. Where is "novelty" in your project?
I just want to say that if you don't know anything about ML/AI, then don't comment anything about it. And worst thing was, he was not ready to accept the fact that for capturing temporal dependencies where underlying probability distribution ia unknown, deep learning performs much better than traditional data analysis techniques.
After hearing his first question, second one was not a surprise for us. We were expecting something like that. For a few moments, we were speechless. Then one of us started by showing neural network architecture. But after some time, he rudely repeated the same question, "where is the algorithm". We told him every fucking thing used in the project, ranging from RMSprop optimizer to Backpropagation through time algorithm to mean squared loss error function.
Then very calmly, he asked third question, why are you using libraries? That moron wanted us to write a whole fucking optimized library. We were speechless at this question. Finally, one of us told him the "obvious" answer. We were completely demotivated. But it didnt end here. The real question was waiting. At the end, after listening to all of us, he dropped the final bomb, WHY HAVE YOU USED A NEURAL NETWORK "ALGORITHM" WHICH HAS ALREADY BEEN IMPLEMENTED? WHY DIDN'T YOU MAKE YOU OWN "ALGORITHM"? We again stated the obvious answer that it takes atleast an year or two of continuous hardwork to develop a state of art algorithm, that too when gou build it on top of some existing "algorithm". After listening to this, he left. His final response was "Try to make a new "algorithm"".
Needless to say, we were completely demotivated after this evaluation. We all had worked too hard for this. And we had ability to explain each and every part of the project intuitively and mathematically, but he was not even ready to listen.
Now, all of us are sitting aimlessly, waiting for Hackathon to end.😢😢😢😢😢25 -
In the begining of time, when The Company was small and The Data could fit in some fucking excel sheets, Those Who Came Before implemented some java tool to issue invoices, notify customers and clear received payments.
Then came the Time Of The Great Expanse, when The Company grew to unthinkable levels. Headcount increased with each passing day, and The Data shows that everything was going great!
But when the future seemed bright, came The Stall-Out. The days when The Company could not expand as fast as it did before. And Those Who Came Before left, abandoning their Undocumented Java Tool to its own luck.
Those who came after knew nothing of the inner workings of the Undocumented Java Tool. They knew only that the magical Jar would take a couple fucking excel spreadsheets and spit out reports and send emails like magic.
And those were The Dark Days.
In the darkness, The Data grew to be a monster. Soon a fucking excel spreadsheet could not hold The Data contained any longer. Those Who Came After, fearing the wrath of The Undocumented Java Tool, dared not mess with its code. Instead, they fucking cut away the lowest volume transactions from the fucking input spreadsheet, and left the company to report the unbilled invoices as "surprise losses". Fucking script kiddies, were Those Who Came After.
Then, at The Darkest of Days (literally, Dec 21st), marched into the project The Six Witchers, who fear not the Demon of Refactoring.
This story is still unfolding. Will The Six Witchers manage to unravel the mysteries of The Undocumented Java Tool? Will they be able to reverse engineer the fucking black box, and scale it's magic into a modern application?
Will they decrease revenue forecasting error by at least 2% in a single strike?
Only the future will tell.16 -
I guess I can also amend in my long, ongoing, storied history of bad calls, failed projections and stellar forecasting that:
- I invested an embarrassing amount of time, money and hope learning Adobe AIR
- I've sent-away for the https://inventhelp.com patent registration kit at least twice
- I've publicly declared that OAuth would never last
- I actually thought Microsoft was onto something with J++
- I bought a bunch of shares of World Wrestling Federation stock the day it went public
- I've stated on my movie podcast that I'll defend until my last breath my argument that Godfather III may be the best film in the series
Can I pick 'em, or what? ;)
---
Part 1 of my bad calls: https://devrant.com/rants/2786266/...10 -
Look at horoscope. Following 3 months will be shit. Is fate in my own hands? Is so, why I cannot change the horoscope forecasting. That means fate was set and I just follow the script of my life. Sad.....12
-
turns out, dealing with time series data is on another level. i clearly still have a lot to learn. finally forecasted 25 days worth of slippage4