Font size
WorksheetsModule 3 (Part 2)
Total questions: 22
Worksheet time: 37mins
You are part of a data science team that is working for a national fast-food chain. You create a simple report that shows trend: Customers who visit the store more often and buy smaller meals spend more than customers who visit less frequently and buy larger meals. What is the most likely diagram that your team created?
multiclass classification diagram
linear regression and scatter plots
Barplot
K-means cluster diagram
classification report
Your company wants to predict whether existing automotive insurance customers are more likely to buy homeowners insurance. It created a model to better predict the best customers contact about homeowners insurance, and the model had a low variance but high bias. What does that say about the data model?
It was consistently wrong.
It was inconsistently wrong.
It was consistently right.
It was equally right end wrong.
You want to identify global weather patterns that may have been affected by climate change. To do so, you want to use machine learning algorithms to find patterns that would otherwise be imperceptible to a human meteorologist. What is the place to start?
Find labeled data of sunny days so that the machine will learn to identify bad weather.
Use unsupervised learning have the machine look for anomalies in a massive weather database.
Create a training set of unusual patterns and ask the machine learning algorithms to classify them.
Create a training set of normal weather and have the machine look for similar patterns.
Asian user complains that your company's facial recognition model does not properly identify their facial expressions. What should you do?
Include Asian faces in your test data and retrain your model.
Retrain your model with updated hyperparameter values.
Retrain your model with smaller batch sizes.
Include Asian faces in your training data and retrain your model.
"you can still make recommendation even if you don’t have specific information about each user" is one of advantage of ...
Model-Based Recommendation
Item-Based Recomendation
Content-Based Recommendation
User-Based Recommendation
Merekomendasikan item M yang belum digunakan oleh pengguna U tetapi dimiliki telah digunakan oleh pengguna lain yang memiliki preferensi yang mirip dengan pengguna U merupakan cara kerja dari metode rekomendasi ...
Model-Based
Item-Based
User-Based
Content-Based
Hierarchical Clustering dan Boosting-Based model merupakan interpretable model
Benar
Salah
“This transaction overall dropped since the new customer transaction is dropped too, we need to find out how to increase new customer now” is an example of a statement from
Correlation
Causality
Predictive Power
"Which customer is at risk to leave our service"
This statement includes a prediction statement
True
False
Companies that already have a "Data-Aware Mindset" have a higher Business Value than companies that have a "Data-Savvy Mindset".
True
False
Saat jumlah data pada node setelah melakukan splitting kurang dari ketentuan, maka proses splitting pada Decision Tree akan berhenti
Benar
Salah
Teknik yang melibatkan kombinasi data dari prediksi beberapa model, yang digunakan sebagai fitur untuk menghasilkan model baru dan membuat prediksi. Model yang digabungkan dikenal sebagai base learner, dan prediksinya yang digunakan sebagai fitur tambahan untuk melatih model akhir dikenal sebagai meta learner.
Stacking
Boosting
Bagging
Random Forest
Teknik Principal Component Analysis (PCA) mengurangi banyak fitur dengan cara meringkas seluruh fitur yang ada menjadi beberapa komponen yang ditentukan.
Benar
Salah
Pada proses text mining, semakin sering suatu kata muncul di dokumen lain maka bobot/nilai TF-IDF nya ...
Semakin besar
Semakin kecil
Konstan
(1) What is making the transaction metrics dropped this morning? -> Business Question ini bersifat inference
(2) Where are our most prestigious customers come from? -> Business Question ini bersifat prediction
(3) Why our voucher and promotion quota runs out today? -> Business Question ini bersifat inference
(4) How to separate fraud and normal users from their behavior? -> Business Question ini bersifat prediction
(5) Which customer is at risk to leave our service? -> Business Question ini bersifat inference
Pilih mana saja pernyataan yang benar..
1
2
3
4
5
Jika kita memilih nilai parameter maximum depth = 10. Maka kesimpulan yang akan didapat yaitu ...
Nilai training accuracy lebih kecil daripada nilai testing accuracy
Model mengalami underfitting
Nilai training accuracy lebih tinggi daripada nilai testing accuracy
Model mengalami overfitting
Model yang dibuat masih terlalu kompleks
(1) Semakin besar nilai parameter min_samples, semakin dalam tree yang dihasilkan.
(2) Semakin besar nilai parameter max_depth, semakin besar kemungkinan untuk terjadi overfitting.
(3) Decision Tree hanya dapat digunakan untuk klasifikasi.
(4) Decision Tree merupakan salah satu interpretable model.
(5) Decision Tree merupakan salah satu model parametrik.
Pilih pernyataan mana saja yang benar !
1
2
3
4
5
(1) Pada analisis Time Series, proses differencing pada data akan mengurangi jumlah data.
(2) Regresi Linear dapat digunakan untuk memprediksi data Time Series.
(3) Saat melakukan analisa Time Series, data harus normal
(4) Decision Tree dapat digunakan untuk memprediksi data Time Series.
(5) Kita dapat melakukan proses Cross-Validation pada data Time Series
Dari 3 pernyataan diatas. Mana pernyataan yang kurang tepat
1
2
3
4
Bagian yang kemungkinan dapat menyebabkan masalah saat pembuatan model yaitu pada baris ke -
(a)
Variabel yang saling berkorelasi pasti saling mempengaruhi
Benar
Salah
Kita dapat menggunakan Decision Tree untuk mengelompokan data
Benar
Salah
Targetted marketing, Recommended Systems, and Customer Segmentation are applications in ...
Unsupervised Learning: Clustering
Unsupervised Learning: Dimentional Reduction
Supervised Learning: Classification
Unsupervised Learning: Regression
Supervised Learning: Regression
