{ "id": 284888, "title": "🔥 Relevant Notebooks from Optiver & Janesteet competitions to start from! 🔥", "url": "/competitions/g-research-crypto-forecasting/discussion/284888", "author_name": "", "post_date": "2021-11-02T18:58:39.885000", "votes": 30, "comment_count": 0, "views": 0, "content": "
\n

Huge credit to @mouafekmk for compiling the original list!
\n Original link: https://www.kaggle.com/c/optiver-realized-volatility-prediction/discussion/249899.
\n If you find this useful, go upvote it!

\n
\n

Optiver volatility prediction is still ongoing at the moment, however, there are some awesome notebooks from it that can totally help here!

\n

Comparison between different fillna methods
\nhttps://www.kaggle.com/c/jane-street-market-prediction/discussion/201302

\n

TensorFlow for Time Series Modeling(new)
\nhttps://www.kaggle.com/c/optiver-realized-volatility-prediction/discussion/249940

\n

Bottleneck encoder + MLP + PurgedGroupTimeSeriesSplit
\nhttps://www.kaggle.com/aimind/bottleneck-encoder-mlp-keras-tuner-8601c5

\n

Bottleneck encoder + MLP + Keras Tuner + GroupTimeSeriesSplit
\nhttps://www.kaggle.com/snippsy/bottleneck-encoder-mlp-keras-tuner

\n

ResNet starter 13bdb8
\nhttps://www.kaggle.com/aimind/resnet-or-1dcnn

\n

Light GBM + Reduce memory usage
\nhttps://www.kaggle.com/binhlc/jane-street-light-gbm

\n

FE for fast inference
\nhttps://www.kaggle.com/lucasmorin/running-algos-fe-for-fast-inference

\n

Introducing CombPurgedKFoldCV
\nhttps://www.kaggle.com/c/jane-street-market-prediction/discussion/216833

\n

Pytorch Resnet Starter Training & Inference
\nhttps://www.kaggle.com/a763337092/pytorch-resnet-starter-training?scriptVersionId=52928216
\nhttps://www.kaggle.com/a763337092/pytorch-resnet-starter-inference/comments?scriptVersionId=52736172

\n

Pytorch-embeddingsNN + Resnet + Tensorflow
\nhttps://www.kaggle.com/sapthrishi007/pytorch-embeddingsnn-resnet-tensorflow/
\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3?scriptVersionId=54213771

\n

FastAI + PyTorch + Embeddings
\nPytorch-embeddingsNN + Resnet + Tensorflow
\nhttps://www.kaggle.com/sapthrishi007/pytorch-embeddingsnn-resnet-tensorflow?scriptVersionId=54790567

\n

Pytorch-embeddingsNN + Resnet + Tensorflow
\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3/output?scriptVersionId=54213771
\nhttps://www.kaggle.com/sagarjiyani/pytorch-embeddingsnn-resnet?scriptVersionId=54925228
\nbased on this
\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3/data?scriptVersionId=53603141&select=Jane_EmbNN5_auc_400_400_400.pth
\nI did execute it here
\nhttps://www.kaggle.com/mouafekmk/fastai-inference-pytorch-embeddingsnn-resnet

\n

pca-xgbclassifier-purgedsplit-optunacv
\nhttps://www.kaggle.com/marcodibartolo/cmu-team-pca-xgbclassifier-purgedsplit-optunacv

\n

encoder-catboost
\nhttps://www.kaggle.com/anatolymal/jsm-v05-1-encoder-catboost

\n

xgboost-trading-classifier
\nhttps://www.kaggle.com/sarvesh278/xgboost-trading-classifier

\n

lightgbm-classifier-pca-logit-on-utility-score
\nhttps://www.kaggle.com/satorushibata/lightgbm-classifier-pca-logit-on-utility-score

\n

optuna-xgbclassifier-parameters-optimize
\nhttps://www.kaggle.com/miklgr500/optuna-xgbclassifier-parameters-optimize

\n

jane-pytorch-lstm-implementation
\nhttps://www.kaggle.com/kwonyoung234/jane-pytorch-lstm-implementation

\n

Train NN and save and load weights(models)
\nhttps://www.kaggle.com/gogo827jz/jane-street-neural-network-starter/comments?scriptVersionId=48765235

\n

Purged TS CV + OPTUNA + PIPE + XGB + GridSearch
\nhttps://www.kaggle.com/marketneutral/purged-time-series-cv-xgboost-optuna

\n

Purged TS CV + HyperOpt + FFill
\nhttps://www.kaggle.com/gogo827jz/jane-street-ffill-xgboost-purgedtimeseriescv

\n

Time Series Split
\nhttps://www.kaggle.com/jorijnsmit/found-the-holy-grail-grouptimeseriessplit

\n

Reduce_memory_usage + TCN
\nhttps://www.kaggle.com/tarriaza/janestreet-tcn-w-double-stacked-autoencoder

\n

Jane Street: Neural Network Starter
\nhttps://www.kaggle.com/gogo827jz/jane-street-neural-network-starter

\n

Blending tensorflow and pytorch
\nhttps://www.kaggle.com/a763337092/blending-tensorflow-and-pytorch

\n

OWN Jane Street with Keras NN
\nhttps://www.kaggle.com/tarlannazarov/own-jane-street-with-keras-nn/

\n

Tensorflow Dense + Keras Tuner (*)
\nhttps://www.kaggle.com/binhlc/jane-street-tensorflow-dense

\n

If you find this useful, go and drop them some upvotes! they deserve it!

\n

Happy Kaggling!
\nCheers ^^

", "messages": [ { "id": 1568436, "postDate": "2021-11-02T18:58:39.887Z", "content": "
\n

Huge credit to @mouafekmk for compiling the original list!
\n Original link: https://www.kaggle.com/c/optiver-realized-volatility-prediction/discussion/249899.
\n If you find this useful, go upvote it!

\n
\n

Optiver volatility prediction is still ongoing at the moment, however, there are some awesome notebooks from it that can totally help here!

\n

Comparison between different fillna methods
\nhttps://www.kaggle.com/c/jane-street-market-prediction/discussion/201302

\n

TensorFlow for Time Series Modeling(new)
\nhttps://www.kaggle.com/c/optiver-realized-volatility-prediction/discussion/249940

\n

Bottleneck encoder + MLP + PurgedGroupTimeSeriesSplit
\nhttps://www.kaggle.com/aimind/bottleneck-encoder-mlp-keras-tuner-8601c5

\n

Bottleneck encoder + MLP + Keras Tuner + GroupTimeSeriesSplit
\nhttps://www.kaggle.com/snippsy/bottleneck-encoder-mlp-keras-tuner

\n

ResNet starter 13bdb8
\nhttps://www.kaggle.com/aimind/resnet-or-1dcnn

\n

Light GBM + Reduce memory usage
\nhttps://www.kaggle.com/binhlc/jane-street-light-gbm

\n

FE for fast inference
\nhttps://www.kaggle.com/lucasmorin/running-algos-fe-for-fast-inference

\n

Introducing CombPurgedKFoldCV
\nhttps://www.kaggle.com/c/jane-street-market-prediction/discussion/216833

\n

Pytorch Resnet Starter Training & Inference
\nhttps://www.kaggle.com/a763337092/pytorch-resnet-starter-training?scriptVersionId=52928216
\nhttps://www.kaggle.com/a763337092/pytorch-resnet-starter-inference/comments?scriptVersionId=52736172

\n

Pytorch-embeddingsNN + Resnet + Tensorflow
\nhttps://www.kaggle.com/sapthrishi007/pytorch-embeddingsnn-resnet-tensorflow/
\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3?scriptVersionId=54213771

\n

FastAI + PyTorch + Embeddings
\nPytorch-embeddingsNN + Resnet + Tensorflow
\nhttps://www.kaggle.com/sapthrishi007/pytorch-embeddingsnn-resnet-tensorflow?scriptVersionId=54790567

\n

Pytorch-embeddingsNN + Resnet + Tensorflow
\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3/output?scriptVersionId=54213771
\nhttps://www.kaggle.com/sagarjiyani/pytorch-embeddingsnn-resnet?scriptVersionId=54925228
\nbased on this
\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3/data?scriptVersionId=53603141&select=Jane_EmbNN5_auc_400_400_400.pth
\nI did execute it here
\nhttps://www.kaggle.com/mouafekmk/fastai-inference-pytorch-embeddingsnn-resnet

\n

pca-xgbclassifier-purgedsplit-optunacv
\nhttps://www.kaggle.com/marcodibartolo/cmu-team-pca-xgbclassifier-purgedsplit-optunacv

\n

encoder-catboost
\nhttps://www.kaggle.com/anatolymal/jsm-v05-1-encoder-catboost

\n

xgboost-trading-classifier
\nhttps://www.kaggle.com/sarvesh278/xgboost-trading-classifier

\n

lightgbm-classifier-pca-logit-on-utility-score
\nhttps://www.kaggle.com/satorushibata/lightgbm-classifier-pca-logit-on-utility-score

\n

optuna-xgbclassifier-parameters-optimize
\nhttps://www.kaggle.com/miklgr500/optuna-xgbclassifier-parameters-optimize

\n

jane-pytorch-lstm-implementation
\nhttps://www.kaggle.com/kwonyoung234/jane-pytorch-lstm-implementation

\n

Train NN and save and load weights(models)
\nhttps://www.kaggle.com/gogo827jz/jane-street-neural-network-starter/comments?scriptVersionId=48765235

\n

Purged TS CV + OPTUNA + PIPE + XGB + GridSearch
\nhttps://www.kaggle.com/marketneutral/purged-time-series-cv-xgboost-optuna

\n

Purged TS CV + HyperOpt + FFill
\nhttps://www.kaggle.com/gogo827jz/jane-street-ffill-xgboost-purgedtimeseriescv

\n

Time Series Split
\nhttps://www.kaggle.com/jorijnsmit/found-the-holy-grail-grouptimeseriessplit

\n

Reduce_memory_usage + TCN
\nhttps://www.kaggle.com/tarriaza/janestreet-tcn-w-double-stacked-autoencoder

\n

Jane Street: Neural Network Starter
\nhttps://www.kaggle.com/gogo827jz/jane-street-neural-network-starter

\n

Blending tensorflow and pytorch
\nhttps://www.kaggle.com/a763337092/blending-tensorflow-and-pytorch

\n

OWN Jane Street with Keras NN
\nhttps://www.kaggle.com/tarlannazarov/own-jane-street-with-keras-nn/

\n

Tensorflow Dense + Keras Tuner (*)
\nhttps://www.kaggle.com/binhlc/jane-street-tensorflow-dense

\n

If you find this useful, go and drop them some upvotes! they deserve it!

\n

Happy Kaggling!
\nCheers ^^

", "rawMarkdown": "> Huge credit to @mouafekmk for compiling the original list!\nOriginal link: https://www.kaggle.com/c/optiver-realized-volatility-prediction/discussion/249899.\nIf you find this useful, go upvote it! \n\nOptiver volatility prediction is still ongoing at the moment, however, there are some awesome notebooks from it that can totally help here! \n\n\n**Comparison between different fillna methods**\nhttps://www.kaggle.com/c/jane-street-market-prediction/discussion/201302\n\n**TensorFlow for Time Series Modeling(new)**\nhttps://www.kaggle.com/c/optiver-realized-volatility-prediction/discussion/249940\n\n**Bottleneck encoder + MLP + PurgedGroupTimeSeriesSplit**\nhttps://www.kaggle.com/aimind/bottleneck-encoder-mlp-keras-tuner-8601c5\n\n**Bottleneck encoder + MLP + Keras Tuner + GroupTimeSeriesSplit**\nhttps://www.kaggle.com/snippsy/bottleneck-encoder-mlp-keras-tuner\n\n**ResNet starter 13bdb8**\nhttps://www.kaggle.com/aimind/resnet-or-1dcnn\n\n**Light GBM + Reduce memory usage**\nhttps://www.kaggle.com/binhlc/jane-street-light-gbm\n\n**FE for fast inference**\nhttps://www.kaggle.com/lucasmorin/running-algos-fe-for-fast-inference\n\n**Introducing CombPurgedKFoldCV**\nhttps://www.kaggle.com/c/jane-street-market-prediction/discussion/216833\n\n**Pytorch Resnet Starter Training & Inference**\nhttps://www.kaggle.com/a763337092/pytorch-resnet-starter-training?scriptVersionId=52928216\nhttps://www.kaggle.com/a763337092/pytorch-resnet-starter-inference/comments?scriptVersionId=52736172\n\n**Pytorch-embeddingsNN + Resnet + Tensorflow**\nhttps://www.kaggle.com/sapthrishi007/pytorch-embeddingsnn-resnet-tensorflow/\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3?scriptVersionId=54213771\n\n**FastAI + PyTorch + Embeddings**\nPytorch-embeddingsNN + Resnet + Tensorflow\nhttps://www.kaggle.com/sapthrishi007/pytorch-embeddingsnn-resnet-tensorflow?scriptVersionId=54790567\n\n**Pytorch-embeddingsNN + Resnet + Tensorflow**\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3/output?scriptVersionId=54213771\nhttps://www.kaggle.com/sagarjiyani/pytorch-embeddingsnn-resnet?scriptVersionId=54925228\nbased on this\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3/data?scriptVersionId=53603141&select=Jane_EmbNN5_auc_400_400_400.pth\nI did execute it here\nhttps://www.kaggle.com/mouafekmk/fastai-inference-pytorch-embeddingsnn-resnet\n\n**pca-xgbclassifier-purgedsplit-optunacv**\nhttps://www.kaggle.com/marcodibartolo/cmu-team-pca-xgbclassifier-purgedsplit-optunacv\n\n**encoder-catboost**\nhttps://www.kaggle.com/anatolymal/jsm-v05-1-encoder-catboost\n\n**xgboost-trading-classifier**\nhttps://www.kaggle.com/sarvesh278/xgboost-trading-classifier\n\n**lightgbm-classifier-pca-logit-on-utility-score**\nhttps://www.kaggle.com/satorushibata/lightgbm-classifier-pca-logit-on-utility-score\n\n**optuna-xgbclassifier-parameters-optimize**\nhttps://www.kaggle.com/miklgr500/optuna-xgbclassifier-parameters-optimize\n\n**jane-pytorch-lstm-implementation**\nhttps://www.kaggle.com/kwonyoung234/jane-pytorch-lstm-implementation\n\n**Train NN and save and load weights(models)**\nhttps://www.kaggle.com/gogo827jz/jane-street-neural-network-starter/comments?scriptVersionId=48765235\n\n**Purged TS CV + OPTUNA + PIPE + XGB + GridSearch**\nhttps://www.kaggle.com/marketneutral/purged-time-series-cv-xgboost-optuna\n\n**Purged TS CV + HyperOpt + FFill**\nhttps://www.kaggle.com/gogo827jz/jane-street-ffill-xgboost-purgedtimeseriescv\n\n**Time Series Split**\nhttps://www.kaggle.com/jorijnsmit/found-the-holy-grail-grouptimeseriessplit\n\n**Reduce_memory_usage + TCN**\nhttps://www.kaggle.com/tarriaza/janestreet-tcn-w-double-stacked-autoencoder\n\n**Jane Street: Neural Network Starter**\nhttps://www.kaggle.com/gogo827jz/jane-street-neural-network-starter\n\n**Blending tensorflow and pytorch**\nhttps://www.kaggle.com/a763337092/blending-tensorflow-and-pytorch\n\n**OWN Jane Street with Keras NN**\nhttps://www.kaggle.com/tarlannazarov/own-jane-street-with-keras-nn/\n\n**Tensorflow Dense + Keras Tuner (*)**\nhttps://www.kaggle.com/binhlc/jane-street-tensorflow-dense\n\nIf you find this useful, go and drop them some upvotes! they deserve it!\n\nHappy Kaggling! \nCheers ^^ \n\n", "votes": 29 } ], "comments": [], "raw_markdown_by_id": { "1568436": "> Huge credit to @mouafekmk for compiling the original list!\nOriginal link: https://www.kaggle.com/c/optiver-realized-volatility-prediction/discussion/249899.\nIf you find this useful, go upvote it! \n\nOptiver volatility prediction is still ongoing at the moment, however, there are some awesome notebooks from it that can totally help here! \n\n\n**Comparison between different fillna methods**\nhttps://www.kaggle.com/c/jane-street-market-prediction/discussion/201302\n\n**TensorFlow for Time Series Modeling(new)**\nhttps://www.kaggle.com/c/optiver-realized-volatility-prediction/discussion/249940\n\n**Bottleneck encoder + MLP + PurgedGroupTimeSeriesSplit**\nhttps://www.kaggle.com/aimind/bottleneck-encoder-mlp-keras-tuner-8601c5\n\n**Bottleneck encoder + MLP + Keras Tuner + GroupTimeSeriesSplit**\nhttps://www.kaggle.com/snippsy/bottleneck-encoder-mlp-keras-tuner\n\n**ResNet starter 13bdb8**\nhttps://www.kaggle.com/aimind/resnet-or-1dcnn\n\n**Light GBM + Reduce memory usage**\nhttps://www.kaggle.com/binhlc/jane-street-light-gbm\n\n**FE for fast inference**\nhttps://www.kaggle.com/lucasmorin/running-algos-fe-for-fast-inference\n\n**Introducing CombPurgedKFoldCV**\nhttps://www.kaggle.com/c/jane-street-market-prediction/discussion/216833\n\n**Pytorch Resnet Starter Training & Inference**\nhttps://www.kaggle.com/a763337092/pytorch-resnet-starter-training?scriptVersionId=52928216\nhttps://www.kaggle.com/a763337092/pytorch-resnet-starter-inference/comments?scriptVersionId=52736172\n\n**Pytorch-embeddingsNN + Resnet + Tensorflow**\nhttps://www.kaggle.com/sapthrishi007/pytorch-embeddingsnn-resnet-tensorflow/\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3?scriptVersionId=54213771\n\n**FastAI + PyTorch + Embeddings**\nPytorch-embeddingsNN + Resnet + Tensorflow\nhttps://www.kaggle.com/sapthrishi007/pytorch-embeddingsnn-resnet-tensorflow?scriptVersionId=54790567\n\n**Pytorch-embeddingsNN + Resnet + Tensorflow**\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3/output?scriptVersionId=54213771\nhttps://www.kaggle.com/sagarjiyani/pytorch-embeddingsnn-resnet?scriptVersionId=54925228\nbased on this\nhttps://www.kaggle.com/sapthrishi007/jane-fastai-featinteraction-embeddingnn5-300x3/data?scriptVersionId=53603141&select=Jane_EmbNN5_auc_400_400_400.pth\nI did execute it here\nhttps://www.kaggle.com/mouafekmk/fastai-inference-pytorch-embeddingsnn-resnet\n\n**pca-xgbclassifier-purgedsplit-optunacv**\nhttps://www.kaggle.com/marcodibartolo/cmu-team-pca-xgbclassifier-purgedsplit-optunacv\n\n**encoder-catboost**\nhttps://www.kaggle.com/anatolymal/jsm-v05-1-encoder-catboost\n\n**xgboost-trading-classifier**\nhttps://www.kaggle.com/sarvesh278/xgboost-trading-classifier\n\n**lightgbm-classifier-pca-logit-on-utility-score**\nhttps://www.kaggle.com/satorushibata/lightgbm-classifier-pca-logit-on-utility-score\n\n**optuna-xgbclassifier-parameters-optimize**\nhttps://www.kaggle.com/miklgr500/optuna-xgbclassifier-parameters-optimize\n\n**jane-pytorch-lstm-implementation**\nhttps://www.kaggle.com/kwonyoung234/jane-pytorch-lstm-implementation\n\n**Train NN and save and load weights(models)**\nhttps://www.kaggle.com/gogo827jz/jane-street-neural-network-starter/comments?scriptVersionId=48765235\n\n**Purged TS CV + OPTUNA + PIPE + XGB + GridSearch**\nhttps://www.kaggle.com/marketneutral/purged-time-series-cv-xgboost-optuna\n\n**Purged TS CV + HyperOpt + FFill**\nhttps://www.kaggle.com/gogo827jz/jane-street-ffill-xgboost-purgedtimeseriescv\n\n**Time Series Split**\nhttps://www.kaggle.com/jorijnsmit/found-the-holy-grail-grouptimeseriessplit\n\n**Reduce_memory_usage + TCN**\nhttps://www.kaggle.com/tarriaza/janestreet-tcn-w-double-stacked-autoencoder\n\n**Jane Street: Neural Network Starter**\nhttps://www.kaggle.com/gogo827jz/jane-street-neural-network-starter\n\n**Blending tensorflow and pytorch**\nhttps://www.kaggle.com/a763337092/blending-tensorflow-and-pytorch\n\n**OWN Jane Street with Keras NN**\nhttps://www.kaggle.com/tarlannazarov/own-jane-street-with-keras-nn/\n\n**Tensorflow Dense + Keras Tuner (*)**\nhttps://www.kaggle.com/binhlc/jane-street-tensorflow-dense\n\nIf you find this useful, go and drop them some upvotes! they deserve it!\n\nHappy Kaggling! \nCheers ^^ \n\n" } }