Stationarity & Seasonality| Time Series Forecasting #1|

Time series anlaysis and forecasting are huge right now. With the enormous business applications that can be created using time series forecasting, it becomes crucial to dive into depth of this subject.
In this video i talk about the following things which are absolutely essential before learning time series models:
1)Stationarity ,
2)Why is stationarity required and how to convert non stationary time series into stationary
3)Seasonality and how to remove seasonality from a time series
4) We will also look at various time series plots to master the skills of identifying if a times series is stationary or not
Recommended Books to get better at Time Series Analysis and Python:
1)Practical Time Series Analysis: amzn.to/31lsLhq
2)Time Series with Python: amzn.to/2Ez073m
3)Hands-On Time Series Analysis with R: amzn.to/3aUxuKq
You can connect with me on linkedin at : / nachiketa-hebbar-86186...
Leave any queries in the comments section and thanks for watching !

[@jinks3669]

Dhanyavaad. As a data scientist I found this was very helpful

[@user-py7jr6yr3v]

amazing content> very superb man i understood each and everything. For this shit i am paying 4 lakh rupees in a university in United states but cannot understand anything here. But this guy made it so simple. Thanks man. Reallly appreciate.

[@anuragpatil5812]

Thanks for the video !! superb explanation

[@louisa123]

Thanks for your videos! I'm new to time series forecasting and your content gives me a good overview. I noticed though while reading more on the topic that you might have mixed up first order differencing with lag difference. What you describe ( Y(t) - Y(t-2) ) seems to be called a lag-2 difference and apparently order is how many times you do the whole process.

[@ankitayadav2690]

its really good vedio to understand concepts,good work

[@visunashokkumar1782]

Mate this is so informative!!!

[@Jevuify]

Nice explanation. Your channel is underrated

[@mehulmehta4981]

Amazing Explanation Brother....

[@abhijeetjain8228]

very well explained keep it up.

[@teetanrobotics5363]

Love the playlist on Time Series Forecasting. Hope you upload more videos.

[@NachiketaHebbar]

Thanks, and yes will definetly put out more!

[@harinatha3102]

This video is worth watching....! Can you please make a video on Augmented Dickey Fuller test.

[@dewanshkumarmishra9378]

Very helpful video ❤

[@siddhijain3802]

Thankyou for such simple explanation! Great!

[@NachiketaHebbar]

Glad it helped!

[@chandu9696]

Well explained. Looking forward to more content.

[@NachiketaHebbar]

Thanks!

[@venkatesh0075]

Superb explaination

[@swapnadeepghosh8546]

bhai apne itna accha knowledge kaha se liya ??... thanks for passing it brother GOD bless you

[@arnavanuj]

You are a Rockstar ❤️

[@lakshyadaulani2110]

please do make a video in mathematical calculation in both statistical tests for stationarity

[@dabblewithd4247]

Dude.... Thankyouuuuu soo much buddy

[@marksathish2783]

superb bro

[@rutvikjaiswal4986]

You are amazing sir !

[@NachiketaHebbar]

Thanks!

[@abhishekagarwal4408]

very nice explanation i wanted to know can i do time series analysis on yearwise median income of men in any particular country???

[@h4rsh261]

I understood the differencing part, but I have a question. If we take the differencing and reduce the scale of data from 400-500 to 0.1-0.5, wont we have trouble scaling the output later ? and if we take the differencing from the data to make it stationary doesnt it mean that we are changing the nature of the data and instead we can use a better model that can work with the current state of data ?

[@dicloniusN35]

in python arima there is auto differencing? we don't need to fit model with this differenced time series? just select 'I' value? second param

[@kavishkagimhani9803]

thank you

[@pragyabhardwaj7112]

Please make a video for statistical test

[@medhavanisharma3323]

Hello Nachiketa Can you just tell me if there is any videos regarding the theory content on this particular topic...

[@luisarmando415]

kudos!

[@venkatkasireddy8928]

Nicee

[@nurulain4167]

Can you share example of forecasting using hybrid models?

[@tinabeigi2493]

Hey, i liked your video, But can you please share the codes for the log operation, etc. Thank you.

[@joshpeters813]

Okay so what is the interpretation of the final result vs the exponential curve?

[@pouriaforouzesh5349]

👍

[@sulagnanandi2024]

how can we get the actual predicted values back when converted data to stationary?

[@dicloniusN35]

do you know answer now?)) i have the same quastion beacause this stationarity convertation is not work for me) same mape

[@tsreenivasulu8757]

are you from VIT Vellore? the background in the video looks like vit hostel

[@poortijain9524]

HI, can you also share these ppts please? :/

[@jairaja6924]

why there should be no seasonality

[@hshrestha2811]

If the time series is stationary, does that mean that there is no white noise?

[@raghavverma120]

That means it doesnt have trend,seasonality,cyclicality

[@raghavverma120]

That is mean and variance are constant.. white noise is when the distribution is stationary mean=0 , constant variance, plus autocorrelation is 0

[@Sindbad232]

dude is 15?