filmov
tv
Analyzing K-Pop Using Machine Learning | Part 3: Model Building
Показать описание
This is part 3 of the tutorial where I build different predictive models and compare the results.
In this video, I build several regression models to predict the number of hours that K-pop fans listen to K-pop and I compare them using the Mean Absolute Error (MAE). I build linear regression, lasso regression, ridge regression, random forest, and XGBoost regression models.
For the tree-based models (random forest and XGBoost), I tune the hyper-parameters to find the optimal models.
I ended up choosing the XGBoost model as the MAE was the lowest and a tree-based model generalize the data well.
⏰
02:23 Multiple Linear Regression
05:33 Lasso Regression
08:19 Ridge Regression
09:01 Random Forest Regressor
10:47 XGBoost
12:06 Comparing Model Performances
Other Links from Import Data
#ImportData #ModelBuilding #KPop
In this video, I build several regression models to predict the number of hours that K-pop fans listen to K-pop and I compare them using the Mean Absolute Error (MAE). I build linear regression, lasso regression, ridge regression, random forest, and XGBoost regression models.
For the tree-based models (random forest and XGBoost), I tune the hyper-parameters to find the optimal models.
I ended up choosing the XGBoost model as the MAE was the lowest and a tree-based model generalize the data well.
⏰
02:23 Multiple Linear Regression
05:33 Lasso Regression
08:19 Ridge Regression
09:01 Random Forest Regressor
10:47 XGBoost
12:06 Comparing Model Performances
Other Links from Import Data
#ImportData #ModelBuilding #KPop
0:21:04
Analyzing K-Pop Using Machine Learning | Part 1: Data Collection and Data Cleaning
0:13:40
Analyzing K-Pop Using Machine Learning | Part 3: Model Building
0:11:40
Analyzing K-Pop Using Machine Learning | Part 4: Model Productionization (Model Deployment)
0:20:35
Analyzing K-Pop Using Machine Learning | Part 2: Exploratory Data Analysis (EDA)
0:16:50
Analyzing K-Pop Using Machine Learning | Part 5: GitHub Documentation & Portfolio Website
0:09:46
MOST SYNCHRONIZED KPOP GROUPS ANALYZED BY A COMPUTER (male version) part 1
0:08:18
A Look into KPOP through Data Analysis
0:25:03
ML Workshop: Analysing K-Pop with Python & Spotify | Part 1: Spotify API, Spotipy, EDA
1:00:24
NVIDIA and Trend Micro Discuss The Current State of AI Adoption in Cybersecurity
0:07:08
MOST CONSISTENT KPOP MAIN DANCERS ANALYSED BY A COMPUTER (machine learning)
0:18:09
Data Analysis with Pandas: K-Pop idols (value_counts, filtering, datetimes)
0:19:09
COMPUTER ANALYSES MOST SYNCHRONIZED KPOP GIRL GROUPS (Part 1) [UPDATED ALGORITHM]
0:14:07
COMPUTER ANALYSES MOST COMPLEX KPOP DANCES (CHORUS AND DANCE BREAKS) [Part 1]
0:08:08
How to improve your dance...with machine learning (feat. BTS, EXO)
0:00:26
unhealthy and healthy bodies in k-pop...
0:02:48
K-POP Using Gen AI for Songs
0:17:31
COMPUTER ANALYSES MOST SYNCHRONIZED KPOP BOY GROUPS (Part 2) [UPDATED ALGORITHM]
0:09:34
Kpop Explained by Data
0:07:41
Data Scientist Breaks Down LOONA's Lyrics
0:03:02
Machine Learning Analyze Wonder Girl
0:01:01
Why ALL Pop Songs Sounds EXACTLY Same #songwriter #popmusic #taylorswift #shorts
0:00:29
🗣️ Jisoo can't speak English... #jisooblackpink
0:02:43
What English words are most common in K-pop songs? (Word Cloud)
0:01:00
How Ai can help you become a kpop idol #kpop #aiinfluencers #aitoday
Комментарии