{ "id": 324736, "title": "Notebooks To Get You Started!", "url": "/competitions/h-and-m-personalized-fashion-recommendations/discussion/324736", "author_name": "", "post_date": "2022-05-13T01:34:14.207000", "votes": 0, "comment_count": 0, "views": 0, "content": "

'

\n

If you can't tell, I'm a big fan of fashion. I like my clothes so much that I never change them! I mean, who isn't, right?
\nBut what I love even more is the leaderboard! so when leaderboard and fashion collide, we party!
\nWhich is why I'm so excited about the h-and-m-personalized-fashion-recommendations competition on kaggle.

\n

This is the perfect opportunity to get started.
\nJust go through the starter notebooks below and you'll be on your way!

\n
\n

H&M Eda First Look by vanguarde

\n
\n

The content in vanguarde's notebook include elegant formatting, and valuable insights.

\n
\n

If you're looking for a breathtaking, inspirational read, look no further! This amazing notebook by vanguarde is exactly what you need. vanguarde's style and elegant formatting will leave you in awe. Every cell is filled with valuable insights that will help you achieve your goals and understand the data better.

\n
\n

Recommend Items Purchased Together by cdeotte

\n
\n

This notebook demonstrates how recommending items that are frequently purchased together is effective

\n
\n

In this notebook, cdeotte is recommending items that are frequently purchased together with a customers' previous purchaes. As simple as that, as powerful as that. This notebook shows that this is a hard baseline to overtake.

\n
\n

H&M Implicit Als Model by julian3833

\n
\n

The Alternating Least Squares algorithm is used here to find the best MAP (minimum average precision) given a set of training data.

\n
\n

ALS is one of the most used ML models for recommender systems. It's a matrix factorization method based on SVD (it's actually an approximated, numerical version of SVD).

\n
\n

H&M Eda And Prediction by gpreda

\n
\n

The methods used by gpreda include descriptive statistics, data visualization, and machine learning.

\n
\n

If you are looking for a wonderful analysis notebook that is written by a world-class kaggler, then you should definitely go through gpreda notebook. The plots created in this notebook is colorful and vivid, which will make it easy and fun to read.

\n
\n

Customers Who Bought This Frequently Buy This by cdeotte

\n
\n

The methods used by cdeotte include RAPIDS cuDF, which speeds up the dataframe search to find pairs of items.

\n
\n

The items that customers buy together can give us a lot of information about what they might want to buy in the future! By using RAPIDS cuDF, cdeotte can speed up the dataframe search to find these pairs of items. With this information, we can predict which items a customer will buy after we observe what they have already bought.

\n
\n

Understanding Mean Average Precision by debarshichanda

\n
\n

debarshichanda uses clear explanations and examples to help readers understand the concept of Mean Average Precision.

\n
\n

If you want to understand what Mean Average Precision is and how to compute it, then this notebook is for you. You will find clear explanations and examples that will help you master this concept. Once you have gone through this notebook, you will be able to compute MAP score with ease and confidence.

\n
\n

H&M Pure Pytorch Baseline by aerdem4

\n
\n

aerdem4 uses pure Pytorch and provides clear code examples that are easy to follow.

\n
\n

I urge you to go through this notebook if you want to learn how to use Pytorch for recommendations systems. aerdem4 does an amazing job of walking you through the basics, and provides clear code examples that are easy to follow. You won't regret it!

\n
\n

H&M EDA RAPIDS And Similarity Recommenders by andradaolteanu

\n
\n

andradaolteanu runs methods of similarity recommenders using RAPIDS.

\n
\n

If you want to learn more about RAPIDS and similarity recommenders, andradaolteanu notebook is a great place to start. You'll find detailed tutorials on how to get set up, as well as how to use the library effectively. andradaolteanu also included some sample code that you can play with and adapt to your own needs.

\n
\n

H&M How To Calculate MAP by kaerunantoka

\n
\n

kaerunantoka uses a variety of methods to show us how to calculate MAP at 12.

\n
\n

If you're looking to improve your understanding of the MAP metric, then you'll want to take a look at kaerunantoka notebook. It provides an excellent walk-through of how to calculate MAP12 using various tricks.

\n
\n

Time Is Our Best Friend V2 by hengzheng

\n
\n

hengzheng uses some basic methods to create an incredibly fast baseline notebook.

\n
\n

If you want a fast baseline, you came to the right place! This notebook shows you how to run a fast baseline for this competition.

\n
\n

Do Customers Buy The Same Products Again by lichtlab

\n
\n

Analyzing customer purchase data in order to answer the question: Customers buy the same products again.

\n
\n

After the score became worse not predicting the same item for the same customer in the same month, lichtlab went to check.

\n
\n

H&M Ensembling How To by titericz

\n
\n

Methods used by titericz include blending predictions from different models and using a clever approach.

\n
\n

To blend predictions from different models, titericz notebook offers a clever approach. By using this technique, you can trust the predictions of a model that would have been discarded due to its high variance when working alone.

\n
\n

H&M Trending Products Weekly by byfone

\n
\n

byfone used trend analysis of the products themselves to come up with the prediction.

\n
\n

If you're looking for a simple trick, look no further than byfone's notebook on weekly trending products. This notebook calculates what's hot right now and use it as prediction.

\n
\n

Detailed EDA Understanding H&M Data by datark1

\n
\n

datark1 uses Exploratory Data Analysis (EDA) and created an incredibly sweet looking notebook!

\n
\n

If you're looking to understand H&M sales data, look no further! This notebook provides a detailed exploration of the data using great EDA techniques.

\n
\n

H&M Collaborative Filtering User User by julian3833

\n
\n

julian3833 uses the collaborative filtering algorithm which is a simple and effective model for this competition.

\n
\n

If you're looking for an easy way to get into the world of collaborative filtering, or you want to improve your skills with a simple, effective model, julian3833's notebook is a great place to start.

", "messages": [ { "id": 1786522, "postDate": "2022-05-13T01:34:14.207Z", "content": "

'

\n

If you can't tell, I'm a big fan of fashion. I like my clothes so much that I never change them! I mean, who isn't, right?
\nBut what I love even more is the leaderboard! so when leaderboard and fashion collide, we party!
\nWhich is why I'm so excited about the h-and-m-personalized-fashion-recommendations competition on kaggle.

\n

This is the perfect opportunity to get started.
\nJust go through the starter notebooks below and you'll be on your way!

\n
\n

H&M Eda First Look by vanguarde

\n
\n

The content in vanguarde's notebook include elegant formatting, and valuable insights.

\n
\n

If you're looking for a breathtaking, inspirational read, look no further! This amazing notebook by vanguarde is exactly what you need. vanguarde's style and elegant formatting will leave you in awe. Every cell is filled with valuable insights that will help you achieve your goals and understand the data better.

\n
\n

Recommend Items Purchased Together by cdeotte

\n
\n

This notebook demonstrates how recommending items that are frequently purchased together is effective

\n
\n

In this notebook, cdeotte is recommending items that are frequently purchased together with a customers' previous purchaes. As simple as that, as powerful as that. This notebook shows that this is a hard baseline to overtake.

\n
\n

H&M Implicit Als Model by julian3833

\n
\n

The Alternating Least Squares algorithm is used here to find the best MAP (minimum average precision) given a set of training data.

\n
\n

ALS is one of the most used ML models for recommender systems. It's a matrix factorization method based on SVD (it's actually an approximated, numerical version of SVD).

\n
\n

H&M Eda And Prediction by gpreda

\n
\n

The methods used by gpreda include descriptive statistics, data visualization, and machine learning.

\n
\n

If you are looking for a wonderful analysis notebook that is written by a world-class kaggler, then you should definitely go through gpreda notebook. The plots created in this notebook is colorful and vivid, which will make it easy and fun to read.

\n
\n

Customers Who Bought This Frequently Buy This by cdeotte

\n
\n

The methods used by cdeotte include RAPIDS cuDF, which speeds up the dataframe search to find pairs of items.

\n
\n

The items that customers buy together can give us a lot of information about what they might want to buy in the future! By using RAPIDS cuDF, cdeotte can speed up the dataframe search to find these pairs of items. With this information, we can predict which items a customer will buy after we observe what they have already bought.

\n
\n

Understanding Mean Average Precision by debarshichanda

\n
\n

debarshichanda uses clear explanations and examples to help readers understand the concept of Mean Average Precision.

\n
\n

If you want to understand what Mean Average Precision is and how to compute it, then this notebook is for you. You will find clear explanations and examples that will help you master this concept. Once you have gone through this notebook, you will be able to compute MAP score with ease and confidence.

\n
\n

H&M Pure Pytorch Baseline by aerdem4

\n
\n

aerdem4 uses pure Pytorch and provides clear code examples that are easy to follow.

\n
\n

I urge you to go through this notebook if you want to learn how to use Pytorch for recommendations systems. aerdem4 does an amazing job of walking you through the basics, and provides clear code examples that are easy to follow. You won't regret it!

\n
\n

H&M EDA RAPIDS And Similarity Recommenders by andradaolteanu

\n
\n

andradaolteanu runs methods of similarity recommenders using RAPIDS.

\n
\n

If you want to learn more about RAPIDS and similarity recommenders, andradaolteanu notebook is a great place to start. You'll find detailed tutorials on how to get set up, as well as how to use the library effectively. andradaolteanu also included some sample code that you can play with and adapt to your own needs.

\n
\n

H&M How To Calculate MAP by kaerunantoka

\n
\n

kaerunantoka uses a variety of methods to show us how to calculate MAP at 12.

\n
\n

If you're looking to improve your understanding of the MAP metric, then you'll want to take a look at kaerunantoka notebook. It provides an excellent walk-through of how to calculate MAP12 using various tricks.

\n
\n

Time Is Our Best Friend V2 by hengzheng

\n
\n

hengzheng uses some basic methods to create an incredibly fast baseline notebook.

\n
\n

If you want a fast baseline, you came to the right place! This notebook shows you how to run a fast baseline for this competition.

\n
\n

Do Customers Buy The Same Products Again by lichtlab

\n
\n

Analyzing customer purchase data in order to answer the question: Customers buy the same products again.

\n
\n

After the score became worse not predicting the same item for the same customer in the same month, lichtlab went to check.

\n
\n

H&M Ensembling How To by titericz

\n
\n

Methods used by titericz include blending predictions from different models and using a clever approach.

\n
\n

To blend predictions from different models, titericz notebook offers a clever approach. By using this technique, you can trust the predictions of a model that would have been discarded due to its high variance when working alone.

\n
\n

H&M Trending Products Weekly by byfone

\n
\n

byfone used trend analysis of the products themselves to come up with the prediction.

\n
\n

If you're looking for a simple trick, look no further than byfone's notebook on weekly trending products. This notebook calculates what's hot right now and use it as prediction.

\n
\n

Detailed EDA Understanding H&M Data by datark1

\n
\n

datark1 uses Exploratory Data Analysis (EDA) and created an incredibly sweet looking notebook!

\n
\n

If you're looking to understand H&M sales data, look no further! This notebook provides a detailed exploration of the data using great EDA techniques.

\n
\n

H&M Collaborative Filtering User User by julian3833

\n
\n

julian3833 uses the collaborative filtering algorithm which is a simple and effective model for this competition.

\n
\n

If you're looking for an easy way to get into the world of collaborative filtering, or you want to improve your skills with a simple, effective model, julian3833's notebook is a great place to start.

", "rawMarkdown": "'\n\nIf you can't tell, I'm a big fan of fashion. I like my clothes so much that I never change them! I mean, who isn't, right?\nBut what I love even more is the leaderboard! so when leaderboard and fashion collide, we party!\nWhich is why I'm so excited about the h-and-m-personalized-fashion-recommendations competition on kaggle.\n\nThis is the perfect opportunity to get started.\nJust go through the starter notebooks below and you'll be on your way!\n\n\n_____\n\n\n**[H&M Eda First Look](https://kaggle.com/vanguarde/h-m-eda-first-look) by vanguarde**\n>The content in vanguarde's notebook include elegant formatting, and valuable insights.\n\nIf you're looking for a breathtaking, inspirational read, look no further! This amazing notebook by vanguarde is exactly what you need. vanguarde's style and elegant formatting will leave you in awe. Every cell is filled with valuable insights that will help you achieve your goals and understand the data better.\n\n\n\n_____\n\n\n[Recommend Items Purchased Together](https://kaggle.com/cdeotte/recommend-items-purchased-together-0-021) by cdeotte\n> This notebook demonstrates how recommending items that are frequently purchased together is effective\n\nIn this notebook, cdeotte is recommending items that are frequently purchased together with a customers' previous purchaes. As simple as that, as powerful as that. This notebook shows that this is a hard baseline to overtake.\n\n\n\n_____\n\n\n**[H&M Implicit Als Model](https://kaggle.com/julian3833/h-m-implicit-als-model-0-014) by julian3833**\n>The Alternating Least Squares algorithm is used here to find the best MAP (minimum average precision) given a set of training data.\n\nALS is one of the most used ML models for recommender systems. It's a matrix factorization method based on SVD (it's actually an approximated, numerical version of SVD).\n\n\n\n_____\n\n\n**[H&M Eda And Prediction](https://kaggle.com/gpreda/h-m-eda-and-prediction) by gpreda**\n>The methods used by gpreda include descriptive statistics, data visualization, and machine learning.\n\nIf you are looking for a wonderful analysis notebook that is written by a world-class kaggler, then you should definitely go through gpreda notebook. The plots created in this notebook is colorful and vivid, which will make it easy and fun to read.\n\n\n\n_____\n\n\n**[Customers Who Bought This Frequently Buy This](https://kaggle.com/cdeotte/customers-who-bought-this-frequently-buy-this) by cdeotte**\n>The methods used by cdeotte include RAPIDS cuDF, which speeds up the dataframe search to find pairs of items.\n\nThe items that customers buy together can give us a lot of information about what they might want to buy in the future! By using RAPIDS cuDF, cdeotte can speed up the dataframe search to find these pairs of items. With this information, we can predict which items a customer will buy after we observe what they have already bought.\n\n\n\n_____\n\n\n**[Understanding Mean Average Precision](https://kaggle.com/debarshichanda/understanding-mean-average-precision) by debarshichanda**\n>debarshichanda uses clear explanations and examples to help readers understand the concept of Mean Average Precision.\n\nIf you want to understand what Mean Average Precision is and how to compute it, then this notebook is for you. You will find clear explanations and examples that will help you master this concept. Once you have gone through this notebook, you will be able to compute MAP score with ease and confidence.\n\n\n\n_____\n\n\n**[H&M Pure Pytorch Baseline](https://kaggle.com/aerdem4/h-m-pure-pytorch-baseline) by aerdem4**\n>aerdem4 uses pure Pytorch and provides clear code examples that are easy to follow.\n\nI urge you to go through this notebook if you want to learn how to use Pytorch for recommendations systems. aerdem4 does an amazing job of walking you through the basics, and provides clear code examples that are easy to follow. You won't regret it!\n\n\n\n_____\n\n\n**[H&M EDA RAPIDS And Similarity Recommenders](https://kaggle.com/andradaolteanu/h-m-eda-rapids-and-similarity-recommenders) by andradaolteanu**\n>andradaolteanu runs methods of similarity recommenders using RAPIDS.\n\nIf you want to learn more about RAPIDS and similarity recommenders, andradaolteanu notebook is a great place to start. You'll find detailed tutorials on how to get set up, as well as how to use the library effectively. andradaolteanu also included some sample code that you can play with and adapt to your own needs.\n\n\n\n_____\n\n\n**[H&M How To Calculate MAP](https://kaggle.com/kaerunantoka/h-m-how-to-calculate-map-12) by kaerunantoka**\n>kaerunantoka uses a variety of methods to show us how to calculate MAP at 12.\n\nIf you're looking to improve your understanding of the MAP metric, then you'll want to take a look at kaerunantoka notebook. It provides an excellent walk-through of how to calculate MAP12 using various tricks.\n\n\n\n_____\n\n\n**[Time Is Our Best Friend V2](https://kaggle.com/hengzheng/time-is-our-best-friend-v2) by hengzheng**\n>hengzheng uses some basic methods to create an incredibly fast baseline notebook.\n\nIf you want a fast baseline, you came to the right place! This notebook shows you how to run a fast baseline for this competition.\n\n\n\n_____\n\n\n**[Do Customers Buy The Same Products Again](https://kaggle.com/lichtlab/do-customers-buy-the-same-products-again) by lichtlab**\n>Analyzing customer purchase data in order to answer the question: Customers buy the same products again.\n\nAfter the score became worse not predicting the same item for the same customer in the same month, lichtlab went to check.\n\n_____\n\n\n**[H&M Ensembling How To](https://kaggle.com/titericz/h-m-ensembling-how-to) by titericz**\n>Methods used by titericz include blending predictions from different models and using a clever approach.\n\nTo blend predictions from different models, titericz notebook offers a clever approach. By using this technique, you can trust the predictions of a model that would have been discarded due to its high variance when working alone.\n\n\n\n_____\n\n\n**[H&M Trending Products Weekly](https://kaggle.com/byfone/h-m-trending-products-weekly) by byfone**\n>byfone used trend analysis of the products themselves to come up with the prediction.\n\nIf you're looking for a simple trick, look no further than byfone's notebook on weekly trending products. This notebook calculates what's hot right now and use it as prediction.\n\n\n\n_____\n\n\n**[Detailed EDA Understanding H&M Data](https://kaggle.com/datark1/detailed-eda-understanding-h-m-data) by datark1**\n>datark1 uses Exploratory Data Analysis (EDA) and created an incredibly sweet looking notebook!\n\nIf you're looking to understand H&M sales data, look no further! This notebook provides a detailed exploration of the data using great EDA techniques.\n\n\n\n_____\n\n\n**[H&M Collaborative Filtering User User](https://kaggle.com/julian3833/h-m-collaborative-filtering-user-user) by julian3833**\n>julian3833 uses the collaborative filtering algorithm which is a simple and effective model for this competition.\n\nIf you're looking for an easy way to get into the world of collaborative filtering, or you want to improve your skills with a simple, effective model, julian3833's notebook is a great place to start.\n\n\n" } ], "comments": [], "raw_markdown_by_id": { "1786522": "'\n\nIf you can't tell, I'm a big fan of fashion. I like my clothes so much that I never change them! I mean, who isn't, right?\nBut what I love even more is the leaderboard! so when leaderboard and fashion collide, we party!\nWhich is why I'm so excited about the h-and-m-personalized-fashion-recommendations competition on kaggle.\n\nThis is the perfect opportunity to get started.\nJust go through the starter notebooks below and you'll be on your way!\n\n\n_____\n\n\n**[H&M Eda First Look](https://kaggle.com/vanguarde/h-m-eda-first-look) by vanguarde**\n>The content in vanguarde's notebook include elegant formatting, and valuable insights.\n\nIf you're looking for a breathtaking, inspirational read, look no further! This amazing notebook by vanguarde is exactly what you need. vanguarde's style and elegant formatting will leave you in awe. Every cell is filled with valuable insights that will help you achieve your goals and understand the data better.\n\n\n\n_____\n\n\n[Recommend Items Purchased Together](https://kaggle.com/cdeotte/recommend-items-purchased-together-0-021) by cdeotte\n> This notebook demonstrates how recommending items that are frequently purchased together is effective\n\nIn this notebook, cdeotte is recommending items that are frequently purchased together with a customers' previous purchaes. As simple as that, as powerful as that. This notebook shows that this is a hard baseline to overtake.\n\n\n\n_____\n\n\n**[H&M Implicit Als Model](https://kaggle.com/julian3833/h-m-implicit-als-model-0-014) by julian3833**\n>The Alternating Least Squares algorithm is used here to find the best MAP (minimum average precision) given a set of training data.\n\nALS is one of the most used ML models for recommender systems. It's a matrix factorization method based on SVD (it's actually an approximated, numerical version of SVD).\n\n\n\n_____\n\n\n**[H&M Eda And Prediction](https://kaggle.com/gpreda/h-m-eda-and-prediction) by gpreda**\n>The methods used by gpreda include descriptive statistics, data visualization, and machine learning.\n\nIf you are looking for a wonderful analysis notebook that is written by a world-class kaggler, then you should definitely go through gpreda notebook. The plots created in this notebook is colorful and vivid, which will make it easy and fun to read.\n\n\n\n_____\n\n\n**[Customers Who Bought This Frequently Buy This](https://kaggle.com/cdeotte/customers-who-bought-this-frequently-buy-this) by cdeotte**\n>The methods used by cdeotte include RAPIDS cuDF, which speeds up the dataframe search to find pairs of items.\n\nThe items that customers buy together can give us a lot of information about what they might want to buy in the future! By using RAPIDS cuDF, cdeotte can speed up the dataframe search to find these pairs of items. With this information, we can predict which items a customer will buy after we observe what they have already bought.\n\n\n\n_____\n\n\n**[Understanding Mean Average Precision](https://kaggle.com/debarshichanda/understanding-mean-average-precision) by debarshichanda**\n>debarshichanda uses clear explanations and examples to help readers understand the concept of Mean Average Precision.\n\nIf you want to understand what Mean Average Precision is and how to compute it, then this notebook is for you. You will find clear explanations and examples that will help you master this concept. Once you have gone through this notebook, you will be able to compute MAP score with ease and confidence.\n\n\n\n_____\n\n\n**[H&M Pure Pytorch Baseline](https://kaggle.com/aerdem4/h-m-pure-pytorch-baseline) by aerdem4**\n>aerdem4 uses pure Pytorch and provides clear code examples that are easy to follow.\n\nI urge you to go through this notebook if you want to learn how to use Pytorch for recommendations systems. aerdem4 does an amazing job of walking you through the basics, and provides clear code examples that are easy to follow. You won't regret it!\n\n\n\n_____\n\n\n**[H&M EDA RAPIDS And Similarity Recommenders](https://kaggle.com/andradaolteanu/h-m-eda-rapids-and-similarity-recommenders) by andradaolteanu**\n>andradaolteanu runs methods of similarity recommenders using RAPIDS.\n\nIf you want to learn more about RAPIDS and similarity recommenders, andradaolteanu notebook is a great place to start. You'll find detailed tutorials on how to get set up, as well as how to use the library effectively. andradaolteanu also included some sample code that you can play with and adapt to your own needs.\n\n\n\n_____\n\n\n**[H&M How To Calculate MAP](https://kaggle.com/kaerunantoka/h-m-how-to-calculate-map-12) by kaerunantoka**\n>kaerunantoka uses a variety of methods to show us how to calculate MAP at 12.\n\nIf you're looking to improve your understanding of the MAP metric, then you'll want to take a look at kaerunantoka notebook. It provides an excellent walk-through of how to calculate MAP12 using various tricks.\n\n\n\n_____\n\n\n**[Time Is Our Best Friend V2](https://kaggle.com/hengzheng/time-is-our-best-friend-v2) by hengzheng**\n>hengzheng uses some basic methods to create an incredibly fast baseline notebook.\n\nIf you want a fast baseline, you came to the right place! This notebook shows you how to run a fast baseline for this competition.\n\n\n\n_____\n\n\n**[Do Customers Buy The Same Products Again](https://kaggle.com/lichtlab/do-customers-buy-the-same-products-again) by lichtlab**\n>Analyzing customer purchase data in order to answer the question: Customers buy the same products again.\n\nAfter the score became worse not predicting the same item for the same customer in the same month, lichtlab went to check.\n\n_____\n\n\n**[H&M Ensembling How To](https://kaggle.com/titericz/h-m-ensembling-how-to) by titericz**\n>Methods used by titericz include blending predictions from different models and using a clever approach.\n\nTo blend predictions from different models, titericz notebook offers a clever approach. By using this technique, you can trust the predictions of a model that would have been discarded due to its high variance when working alone.\n\n\n\n_____\n\n\n**[H&M Trending Products Weekly](https://kaggle.com/byfone/h-m-trending-products-weekly) by byfone**\n>byfone used trend analysis of the products themselves to come up with the prediction.\n\nIf you're looking for a simple trick, look no further than byfone's notebook on weekly trending products. This notebook calculates what's hot right now and use it as prediction.\n\n\n\n_____\n\n\n**[Detailed EDA Understanding H&M Data](https://kaggle.com/datark1/detailed-eda-understanding-h-m-data) by datark1**\n>datark1 uses Exploratory Data Analysis (EDA) and created an incredibly sweet looking notebook!\n\nIf you're looking to understand H&M sales data, look no further! This notebook provides a detailed exploration of the data using great EDA techniques.\n\n\n\n_____\n\n\n**[H&M Collaborative Filtering User User](https://kaggle.com/julian3833/h-m-collaborative-filtering-user-user) by julian3833**\n>julian3833 uses the collaborative filtering algorithm which is a simple and effective model for this competition.\n\nIf you're looking for an easy way to get into the world of collaborative filtering, or you want to improve your skills with a simple, effective model, julian3833's notebook is a great place to start.\n\n\n" } }