Time Series Exponential smoothing | Exponential smoothing in time series-must know concept

Time Series Exponential smoothing | Exponential smoothing in time series-must know concept

Hello,
My name is Aman and I am a data scientist.

About this video:
In this video I explain about exponential smoothing of time series. I explain how exponential formula works and what are the different formula for time series exponential smoothing. I also explain the concept of additive and multiplicative time series in this video. Below topics are explained in this video:
1. Exponential smoothing in time series
2. Types of time series exponential smoothing
3. Additive and multiplicative time series
4. Use of time series smoothing
5. Exponential smoothing in python

About Unfold Data science: This channel is to help people understand basics of data science through simple examples in easy way. Anybody without having prior knowledge of computer programming or statistics or machine learning and artificial intelligence can get an understanding of data science at high level through this channel. The videos uploaded will not be very technical in nature and hence it can be easily grasped by viewers from different background as well.

Join Facebook group :

Follow on twitter : @unfoldds

Follow on Instagram : unfolddatascience

Watch python for data science playlist here:

Watch statistics and mathematics playlist here :

Watch End to End Implementation of a simple machine learning model in Python here:

Learn Ensemble Model, Bagging and Boosting here:

Build Career in Data Science Playlist:

Artificial Neural Network and Deep Learning Playlist:

Natural langugae Processing playlist:

Understanding and building recommendation system:

Access all my codes here:

[AnujKinge]

One of the most underrated channels for Data Science. The channel truly deserves a million subscribers

[akshayingole]

Thanks a lot sir you made this tough concept so easy to understand that i will remember it very effectively without any confussion

[alphaq]

I have a doubt sir. Do we choose Alpha value based on our wish or is it determined out of something?

[santoshsahu-oyvo]

You are a good teacher...
Thank you so much for this video...

In This video, I have confusion...
Not clearing the theory concept after mid of this video.
Could you please here sir?

[NitishKumar-zdej]

Thank you Aman for the explanation.
One doubt with respect to Triple Exponential Smoothing: You have used gamma to compute C(t). I believe the value of C(t) = gamma times (x[t]/y[t]) + (1-gamma) times C(t-l) . However, you have written in the video (1-alpha) in stead of (1-gamma) while multiplying with C(t-l). Please clarify whether the 2nd multiplication should have (1-alpha) or (1-gamma). Thanks

[Rajeshmane]

It is great to watch this video, thy way you explain is amazing.

[jijopvarkey]

Such a concept was explained so well..
Thank you..

[WenPan]

Thank you very much for this clear and concise explanation of exponential smoothing.

Wish you all the best :)

[meysamjavadzadeh]

tnx man really helpful and joyful explaining keep making videos 👌💣❤

[farogatolimjonova]

Thank you a lot! It is much more understandable now

[murphyslaw]

Dear Amant,
Very nice explanation.
Do you have any video that explain the below topics?
1. Cover windowed/convolution smoothing
2. Lowess
As i am a beginner, it will be helpful if you have any sample python code for Convolution, Lowess and exponential smoothing for practical understanding.

[mattym]

Thank you very much! Cheers from Toronto 😎

[RajaKishore-sr]

Dear Aman, How about the 'Cyclical' component. What are your thoughts on that.

[TheOraware]

Very nice explanation, does exponential smoothing work on few number of records? Suppose I have 5 years student enrollement data from 2018 to 2022 and want to forecast number of enrollment for 2023, can it be achievable by exponential smoothing? There is only yearly data available not monthly, not weekly/daily. After every end of year we have how many students enrolled this year and based on these previous and current years we want to forecast number of students before starting next year

[moodysaleh]

I used Neural Prophet to forecast a time series for electric load usage. One of the options, asks whether I want to use holidays as a feature and whether they should be additive or multiplicative. Knowing that during holidays and weekends, the electric usage drop to the minimum level, which one do you think makes more sense, additive or multiplicative for holidays/weekends? I am assuming additive, especially since the whole average of the time series is not increasing

[padmaprasad]

Thank you for the explanation. Quick question, Does exponential smoothing apply to compositional data?

[muhammadmasudtarek]

last equation for Ct; is it (1-alpha) or (1-gamma)? just want to be sure.

[subhasisdutta]

when do we get negative predictions and what's the reason for negative forecast basically in time series ?

[mixysujith]

Sir
Very much useful.
Excellent presentation.
Can i get explanation for time series anomaly detection with examples and some models

[lovleenkaur]

Great work... Can u recomend a book for it?