{"id":19307380,"url":"https://github.com/artefactory/choice-learn","last_synced_at":"2025-04-06T02:09:46.293Z","repository":{"id":241297915,"uuid":"733053529","full_name":"artefactory/choice-learn","owner":"artefactory","description":"Discrete choice modeling in Python with large datasets \u0026 models - Assortment \u0026 Pricing Optimization .","archived":false,"fork":false,"pushed_at":"2025-03-28T16:33:10.000Z","size":22527,"stargazers_count":52,"open_issues_count":21,"forks_count":7,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-30T00:05:34.001Z","etag":null,"topics":["assortment","choice","choice-model","choice-modeling","conditional-logit-model","deep","discrete","discrete-choice-models","gurobi","learning","machine","ml","model","neural-networks","optimization","or-tools","pricing","rum","supermarket","tensorflow"],"latest_commit_sha":null,"homepage":"https://artefactory.github.io/choice-learn","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/artefactory.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.bib","codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-12-18T13:09:29.000Z","updated_at":"2025-03-26T14:19:08.000Z","dependencies_parsed_at":"2024-06-26T10:42:09.415Z","dependency_job_id":"6c48a0f6-764c-4326-bfff-9af92796c041","html_url":"https://github.com/artefactory/choice-learn","commit_stats":{"total_commits":622,"total_committers":10,"mean_commits":62.2,"dds":0.04662379421221863,"last_synced_commit":"d035e15c1d53f7e4fc0e321ad302d30a6a1a7f8f"},"previous_names":["artefactory/choice-learn"],"tags_count":11,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/artefactory%2Fchoice-learn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/artefactory%2Fchoice-learn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/artefactory%2Fchoice-learn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/artefactory%2Fchoice-learn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/artefactory","download_url":"https://codeload.github.com/artefactory/choice-learn/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247423515,"owners_count":20936626,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["assortment","choice","choice-model","choice-modeling","conditional-logit-model","deep","discrete","discrete-choice-models","gurobi","learning","machine","ml","model","neural-networks","optimization","or-tools","pricing","rum","supermarket","tensorflow"],"created_at":"2024-11-10T00:10:44.470Z","updated_at":"2025-04-06T02:09:46.277Z","avatar_url":"https://github.com/artefactory.png","language":"Python","readme":"\u003cdiv align=\"center\"\u003e\n\n\u003cpicture\u003e\n  \u003csource media=\"(prefers-color-scheme: light)\" srcset=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/logo_choice_learn.png\"\u003e\n  \u003csource media=\"(prefers-color-scheme: dark)\" srcset=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/white_logo_choice_learn.png\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/refs/heads/white_logo/docs/white_logo_choice_learn.png\" width=\"300\"\u003e\n\u003c/picture\u003e\n\n*Large-scale choice modeling through the lens of machine learning*\n\n[![CI status](https://github.com/artefactory/choice-learn/actions/workflows/ci.yaml/badge.svg)](https://github.com/artefactory/choice-learn/actions/workflows/ci.yaml?query=branch%3Amain)\n[![Linting , formatting, imports sorting: ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)\n[![security: bandit](https://img.shields.io/badge/security-bandit-yellow.svg)](https://github.com/PyCQA/bandit)\n[![Pre-commit](https://img.shields.io/badge/pre--commit-enabled-informational?logo=pre-commit\u0026logoColor=white)](https://github.com/artefactory/choice-learn/blob/main/.pre-commit-config.yaml)\n\n\n![PyPI - Python Version](https://img.shields.io/pypi/pyversions/choice-learn?logo=python)\n![PyPI - Version](https://img.shields.io/pypi/v/choice-learn)\n![PyPI - License](https://img.shields.io/pypi/l/choice-learn?color=purple)\n\n[![DOI](https://joss.theoj.org/papers/10.21105/joss.06899/status.svg)](https://doi.org/10.21105/joss.06899)\n[![cite](https://img.shields.io/badge/Citation-BibTeX-cyan)](./CITATION.bib)\n\u003c/div\u003e\n\n\nChoice-Learn is a Python package designed to help you formulate, estimate, and deploy discrete choice models, e.g., for assortment planning.\nThe package provides ready-to-use datasets and models studied in the academic literature. It also provides a lower level use if you wish to customize the specification of the choice model or formulate your own model from scratch. Choice-Learn efficiently handles large-scale choice data by limiting RAM usage.\n\nChoice-Learn uses NumPy and pandas as data backend engines and TensorFlow for models.\n\n## :trident: Table of Contents\n  - [Introduction - Discrete Choice modeling](#trident-introduction---discrete-choice-modeling)\n  - [What's in there ?](#trident-whats-in-there-)\n  - [Getting Started](#trident-getting-started)\n  - [Installation](#trident-installation)\n  - [Usage](#trident-usage)\n  - [Documentation](#trident-documentation)\n  - [Contributing](#trident-contributing)\n  - [Citation](#trident-citation)\n  - [References](#trident-references)\n\n## :trident: Introduction - Discrete Choice modeling\n\nDiscrete choice models aim at explaining or predicting choices over a set of alternatives. Well known use-cases include analyzing people's choice of mean of transport or products purchases in stores.\n\nIf you are new to choice modeling, you can check this [resource](https://www.publichealth.columbia.edu/research/population-health-methods/discrete-choice-model-and-analysis). The different notebooks from the [Getting Started](#trident-getting-started) section can also help you understand choice modeling and more importantly help you for your usecase.\n\n## :trident: What's in there ?\n\n### Data\n- The **ChoiceDataset** class can handle choice datasets with efficient memory management. It can be used on your own dataset. [[Example]](notebooks/introduction/2_data_handling.ipynb)\n- Many academic datasets are integrated in the library and ready to be used:\n\n| Dataset    | Raw Data | Origin | *from choice_learn.datasets import* | Doc |\n| ---------- | :----: | ------ | ------ | :---: |\n| SwissMetro  | [csv](./choice_learn/datasets/data/swissmetro.csv.gz) | Bierlaire et al. (2001) [[2]](#trident-references) | *load_swissmetro* | [#](https://artefactory.github.io/choice-learn/references/datasets/references_base/#choice_learn.datasets.base.load_swissmetro) |\n| ModeCanada | [csv](./choice_learn/datasets/data/ModeCanada.csv.gz) | Forinash and Koppelman (1993) [[3]](#trident-references) | *load_modecanada* | [#](https://artefactory.github.io/choice-learn/references/datasets/references_base/#choice_learn.datasets.base.load_modecanada) |\n| Train    | [csv](./choice_learn/datasets/data/train_data.csv.gz) | Ben-Akiva et al. (1993) [[5]](#trident-references) |*load_train* | [#](https://artefactory.github.io/choice-learn/references/datasets/references_base/#choice_learn.datasets.base.load_train) |\n| Heating | [csv](./choice_learn/datasets/data/heating_data.csv.gz) | Kenneth Train's [website](https://eml.berkeley.edu/~train/) | *load_heating* | [#](https://artefactory.github.io/choice-learn/references/datasets/references_base/#choice_learn.datasets.base.load_heating) |\n| HC | [csv](./choice_learn/datasets/data/HC.csv.gz) | Kenneth Train's [website](https://eml.berkeley.edu/~train/) | *load_hc* | [#](https://artefactory.github.io/choice-learn/references/datasets/references_base/#choice_learn.datasets.base.load_hc) |\n| Electricity | [csv](./choice_learn/datasets/data/electricity.csv.gz) | Kenneth Train's [website](https://eml.berkeley.edu/~train/) | *load_electricity* | [#](https://artefactory.github.io/choice-learn/references/datasets/references_base/#choice_learn.datasets.base.load_electricity) |\n| Stated Car Preferences | [csv](./choice_learn/datasets/data/car.csv.gz) | McFadden and Train (2000) [[9]](#trident-references) | *load_car_preferences* | [#](https://artefactory.github.io/choice-learn/references/datasets/references_base/#choice_learn.datasets.base.load_car_preferences) |\n| TaFeng Grocery Dataset | [csv](./choice_learn/datasets/data/ta_feng.csv.zip) | [Kaggle](https://www.kaggle.com/datasets/chiranjivdas09/ta-feng-grocery-dataset) | *load_tafeng* | [#](https://artefactory.github.io/choice-learn/references/datasets/references_tafeng/) |\n| ICDM-2013 Expedia | [url](https://www.kaggle.com/c/expedia-personalized-sort) |  Ben Hamner and Friedman (2013) [[6]](#trident-references) | *load_expedia* | [#](https://artefactory.github.io/choice-learn/references/datasets/references_expedia/) |\n| London Passenger Mode Choice | [url]() | Hillel et al. (2018) [[11]](#trident-references) | *load_londonpassenger* | [#](https://artefactory.github.io/choice-learn/references/datasets/references_base/#choice_learn.datasets.base.load_londonpassenger) |\n\n\n### Model estimation\n- Different models are already implemented. You can import and parametrize the models for your own usage.\n- Otherwise, **custom modeling** is made easy by subclassing the ChoiceModel class and specifying your own utility function. [[Example]](notebooks/introduction/4_model_customization.ipynb)\n\n*List of implemented \u0026 ready-to-use models:*\n| Model | Example | Colab | Related Paper | *from choice_learn.models import* | Doc |\n| ---------- | -------- | -------- | ------ | ------ | :---: |\n| MNL | [notebook](notebooks/models/simple_mnl.ipynb) | [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/models/simple_mnl.ipynb) | | *SimpleMNL* | [#](https://artefactory.github.io/choice-learn/references/models/references_simple_mnl/) |\n| Conditional Logit | [notebook](notebooks/introduction/3_model_clogit.ipynb) | [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/introduction/3_model_clogit.ipynb) | Train et al. [[4]](#trident-references) \u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;| *ConditionalLogit* | [#](https://artefactory.github.io/choice-learn/references/models/references_clogit/) |\n| Nested Logit | [notebook](notebooks/models/nested_logit.ipynb) | [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/models/nested_logit.ipynb) | McFadden [[10]](#trident-references)  | *NestedLogit* | [#](https://artefactory.github.io/choice-learn/references/models/references_nested_logit/) |\n| Latent Class MNL | [notebook](notebooks/models/latent_class_model.ipynb) | [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/models/latent_class_model.ipynb) | | *LatentClassConditionalLogit* | [#](https://artefactory.github.io/choice-learn/references/models/references_latent_class_mnl/) |\n| Halo MNL | [notebook](notebooks/models/halo_mnl.ipynb) | [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/models/halo_mnl.ipynb) | Maragheh et al. [[14]](#trident-references) | *HaloMNL* | [#](https://artefactory.github.io/choice-learn/references/models/halo_mnl/) |\n| Low-Rank Halo MNL | [notebook](notebooks/models/halo_mnl.ipynb) | [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/models/halo_mnl.ipynb) | Ko and Li [[15]](#trident-references) | *LowRankHaloMNL* | [#](https://artefactory.github.io/choice-learn/references/models/halo_mnl/) |\n\n| NN-based Model | Example | Colab | Related Paper | *from choice_learn.models import* | Doc |\n| ---------- | -------- | ------ | ---- | ------ | :---: |\n| RUMnet| [notebook](notebooks/models/rumnet.ipynb) | [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/models/rumnet.ipynb) | Aouad and Désir [[1]](#trident-references) | *RUMnet* | [#](https://artefactory.github.io/choice-learn/references/models/references_rumnet/#choice_learn.models.rumnet.PaperRUMnet) |\n| TasteNet | [notebook](notebooks/models/tastenet.ipynb) | [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/models/tastenet.ipynb) | Han et al. [[7]](#trident-references) | *TasteNet* | [#](https://artefactory.github.io/choice-learn/references/models/references_tastenet/) |\n| Learning-MNL | [notebook](notebooks/models/learning_mnl.ipynb) | [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/models/learning_mnl.ipynb) | Sifringer et al. [[13]](#trident-references) | *LearningMNL* | [#](https://artefactory.github.io/choice-learn/references/models/references_learning_mnl/) |\n| ResLogit | [notebook](notebooks/models/reslogit.ipynb) | [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/models/reslogit.ipynb) | Wong and Farooq [[12]](#trident-references) | *ResLogit* | [#](https://artefactory.github.io/choice-learn/references/models/references_reslogit/) |\n\n| Basket Model | Example | Colab | Related Paper | *from choice_learn.basket_models import* | Doc |\n| ---------- | -------- | ------ | ---- | ------ | :---: |\n| SHOPPER| [notebook](notebooks/basket_models/shopper.ipynb) | [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/basket_models/shopper.ipynb) | Ruiz et al. [[16]](#trident-references) | *Shopper* | [#](https://artefactory.github.io/choice-learn/references/basket_models/references_shopper/) |\n\n\n### Auxiliary tools\nAlgorithms leveraging choice models are integrated within the library:\n- Assortment \u0026 Pricing optimization algorithms [[Example]](notebooks/auxiliary_tools/assortment_example.ipynb) [[8]](#trident-references) [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/auxiliary_tools/assortment_example.ipynb)\n\n## :trident: Getting Started\n\nYou can find the following tutorials to help you getting started with the package:\n- Generic and simple introduction [[notebook]](notebooks/introduction/1_introductive_example.ipynb)[[doc]](https://expert-dollop-1wemk8l.pages.github.io/notebooks/introduction/1_introductive_example/) [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab\n)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/introduction/1_introductive_example.ipynb)\n- Detailed explanations of data handling depending on the data format [[noteboook]](notebooks/introduction/2_data_handling.ipynb)[[doc]](https://expert-dollop-1wemk8l.pages.github.io/notebooks/introduction/2_data_handling/)  [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/introduction/2_data_handling.ipynb)\n- A detailed example of conditional logit estimation [[notebook]](notebooks/introduction/3_model_clogit.ipynb)[[doc]](https://expert-dollop-1wemk8l.pages.github.io/notebooks/introduction/3_model_clogit/)  [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/introduction/3_model_clogit.ipynb)\n- Introduction to custom modeling and more complex parametrization [[notebook]](notebooks/introduction/4_model_customization.ipynb)[[doc]](https://expert-dollop-1wemk8l.pages.github.io/notebooks/introduction/4_model_customization/) [![Open In Colab](https://img.shields.io/badge/-grey?logo=googlecolab)](https://colab.research.google.com/github/artefactory/choice-learn/blob/main/notebooks/introduction/4_model_customization.ipynb)\n- All models and algorithms have a companion example in the notebook [directory](./notebooks/)\n\n## :trident: Installation\n\n### User installation\n\nTo install the required packages in a virtual environment, run the following command:\n\nThe easiest is to pip-install the package:\n```bash\npip install choice-learn\n```\n\nOtherwise you can use the git repository to get the latest version:\n```bash\ngit clone git@github.com:artefactory/choice-learn.git\n```\n\n### Dependencies\nFor manual installation, Choice-Learn requires the following:\n- Python (\u003e=3.9, \u003c3.13)\n- NumPy (\u003e=1.24)\n- pandas (\u003e=1.5)\n\nFor modeling you need:\n- TensorFlow (\u003e=2.14, \u003c2.17)\n\n\u003e :warning: **Warning:** If you are a MAC user with a M1 or M2 chip, importing TensorFlow might lead to Python crashing.\n\u003e In such case, use anaconda to install TensorFlow with `conda install -c apple tensorflow`.\n\nAn optional requirement used for coefficients analysis and L-BFGS optimization is:\n- TensorFlow Probability (\u003e=0.22)\n\nFinally for pricing or assortment optimization, you need either Gurobi or OR-Tools:\n- gurobipy (\u003e=11.0)\n- ortools (\u003e=9.6)\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://numpy.org/\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/numpy_logo.png\" width=\"60\" /\u003e\n  \u003c/a\u003e\n  \u0026nbsp;\n  \u0026nbsp;\n  \u003ca href=\"https://pandas.pydata.org/\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/pandas_logo.png\" width=\"60\" /\u003e\n  \u003c/a\u003e\n  \u0026nbsp;\n  \u0026nbsp;\n  \u003ca href=\"https://www.tensorflow.org\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/tf_logo.png\" width=\"60\" /\u003e\n  \u003c/a\u003e\n  \u0026nbsp;\n  \u0026nbsp;\n  \u003ca href=\"https://www.gurobi.com/\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/gurobi_logo.png\" width=\"60\" /\u003e\n  \u003c/a\u003e\n  \u0026nbsp;\n  \u0026nbsp;\n  \u003ca href=\"https://developers.google.com/optimization?hl=fr\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/or_tools_logo.png\" width=\"70\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003e :bulb: **Tip:** You can use the poetry.lock or requirements-complete.txt files with poetry or pip to install a fully predetermined and working environment.\n\n## :trident: Usage\nHere is a short example of model parametrization to estimate a Conditional Logit on the ModeCanada dataset.\n\n```python\nfrom choice_learn.data import ChoiceDataset\nfrom choice_learn.models import ConditionalLogit, RUMnet\nfrom choice_learn.datasets import load_modecanada\n\ntransport_df = load_modecanada(as_frame=True)\n# Instantiation of a ChoiceDataset from a pandas.DataFrame\ndataset = ChoiceDataset.from_single_long_df(df=transport_df,\n                                            items_id_column=\"alt\",\n                                            choices_id_column=\"case\",\n                                            choices_column=\"choice\",\n                                            shared_features_columns=[\"income\"],\n                                            items_features_columns=[\"cost\", \"freq\", \"ovt\", \"ivt\"],\n                                            choice_format=\"one_zero\")\n\n# Initialization of the model\nmodel = ConditionalLogit()\n\n# Creation of the different weights:\n\n# add_coefficients adds one coefficient for each specified item_index\n# intercept, and income are added for each item except the first one that needs to be zeroed\nmodel.add_coefficients(feature_name=\"intercept\",\n                       items_indexes=[1, 2, 3])\nmodel.add_coefficients(feature_name=\"income\",\n                       items_indexes=[1, 2, 3])\nmodel.add_coefficients(feature_name=\"ivt\",\n                       items_indexes=[0, 1, 2, 3])\n\n# add_shared_coefficient add one coefficient that is used for all items specified in the items_indexes:\n# Here, cost, freq and ovt coefficients are shared between all items\nmodel.add_shared_coefficient(feature_name=\"cost\",\n                             items_indexes=[0, 1, 2, 3])\nmodel.add_shared_coefficient(feature_name=\"freq\",\n                             items_indexes=[0, 1, 2, 3])\nmodel.add_shared_coefficient(feature_name=\"ovt\",\n                             items_indexes=[0, 1, 2, 3])\n\nhistory = model.fit(dataset, get_report=True)\nprint(\"The average neg-loglikelihood is:\", model.evaluate(dataset).numpy())\nprint(model.report)\n```\n\n## :trident: Documentation\n\nA detailed documentation of this project is available [here](https://artefactory.github.io/choice-learn/).\\\nTensorFlow also has extensive [documentation](https://www.tensorflow.org/) that can help you.\\\nAn academic paper has been published in the Journal of Open-Source Software, [here](https://joss.theoj.org/papers/10.21105/joss.06899).\n\n## :trident: Contributing\nYou are welcome to contribute to the project ! You can help in various ways:\n- raise issues\n- resolve issues already opened\n- develop new features\n- provide additional examples of use\n- fix typos, improve code quality\n- develop new tests\n\nWe recommend to first open an [issue](https://github.com/artefactory/choice-learn/issues) to discuss your ideas. More details are given [here](./CONTRIBUTING.md).\n\n## :trident: Citation\n\nIf you consider this package and any of its feature useful for your research, consider citing our [paper](https://joss.theoj.org/papers/10.21105/joss.06899).\n\n\u003ca href=\"https://joss.theoj.org/papers/10.21105/joss.06899\"\u003e\n\u003cimg align=\"left\" width=\"100\"src=\"https://github.com/openjournals/joss/blob/main/docs/logos/joss-logo.png?raw=true\" /\u003e\n\u003c/a\u003e\n\n```bash\n@article{Auriau2024,\n  doi = {10.21105/joss.06899},\n  url = {https://doi.org/10.21105/joss.06899},\n  year = {2024},\n  publisher = {The Open Journal},\n  volume = {9},\n  number = {101},\n  pages = {6899},\n  author = {Vincent Auriau and Ali Aouad and Antoine Désir and Emmanuel Malherbe},\n  title = {Choice-Learn: Large-scale choice modeling for operational contexts through the lens of machine learning},\n  journal = {Journal of Open Source Software} }\n```\n\n### License\n\nThe use of this software is under the MIT license, with no limitation of usage, including for commercial applications.\n\n### Affiliations\n\nChoice-Learn has been developed through a collaboration between researchers at the Artefact Research Center and the laboratory MICS from CentraleSupélec, Université Paris Saclay.\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://www.artefact.com/data-consulting-transformation/artefact-research-center/\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/logo_arc.png\" height=\"60\" /\u003e\n  \u003c/a\u003e\n  \u0026emsp;\n  \u0026emsp;\n  \u003ca href=\"https://www.artefact.com/\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/logo_atf.png\" height=\"65\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://www.universite-paris-saclay.fr/\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/logo_paris_saclay.png\" height=\"60\" /\u003e\n  \u003c/a\u003e\n  \u0026emsp;\n  \u0026emsp;\n  \u003ca href=\"https://mics.centralesupelec.fr/\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/logo_CS.png\" height=\"60\" /\u003e\n  \u003c/a\u003e\n  \u0026emsp;\n  \u0026emsp;\n  \u003ca href=\"https://www.london.edu/\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/logo_lbs.jpeg\" height=\"60\" /\u003e\n  \u003c/a\u003e\n  \u0026emsp;\n  \u0026emsp;\n  \u003ca href=\"https://www.insead.edu/\"\u003e\n    \u003cimg src=\"https://raw.githubusercontent.com/artefactory/choice-learn/main/docs/illustrations/logos/logo_insead.png\" height=\"60\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n## :trident: References\n\n### Papers\n[1][Representing Random Utility Choice Models with Neural Networks](https://arxiv.org/abs/2207.12877), Aouad, A.; Désir, A. (2022)\\\n[2][The Acceptance of Model Innovation: The Case of Swissmetro](https://www.researchgate.net/publication/37456549_The_acceptance_of_modal_innovation_The_case_of_Swissmetro), Bierlaire, M.; Axhausen, K., W.; Abay, G. (2001)\\\n[3][Applications and Interpretation of Nested Logit Models of Intercity Mode Choice](https://trid.trb.org/view/385097), Forinash, C., V.; Koppelman, F., S. (1993)\\\n[4][The Demand for Local Telephone Service: A Fully Discrete Model of Residential Calling Patterns and Service Choices](https://www.jstor.org/stable/2555538), Train K., E.; McFadden, D., L.; Moshe, B. (1987)\\\n[5] [Estimation of Travel Choice Models with Randomly Distributed Values of Time](https://ideas.repec.org/p/fth/lavaen/9303.html), Ben-Akiva, M.; Bolduc, D.; Bradley, M. (1993)\\\n[6] [Personalize Expedia Hotel Searches - ICDM 2013](https://www.kaggle.com/c/expedia-personalized-sort), Ben Hamner, A.; Friedman, D.; SSA_Expedia. (2013)\\\n[7] [A Neural-embedded Discrete Choice Model: Learning Taste Representation with Strengthened Interpretability](https://arxiv.org/abs/2002.00922), Han, Y.; Calara Oereuran F.; Ben-Akiva, M.; Zegras, C. (2020)\\\n[8] [A branch-and-cut algorithm for the latent-class logit assortment problem](https://www.sciencedirect.com/science/article/pii/S0166218X12001072), Méndez-Díaz, I.; Miranda-Bront, J. J.; Vulcano, G.; Zabala, P. (2014)\\\n[9] [Stated Preferences for Car Choice in Mixed MNL models for discrete response.](https://www.jstor.org/stable/2678603), McFadden, D. and Kenneth Train (2000)\\\n[10] [Modeling the Choice of Residential Location](https://onlinepubs.trb.org/Onlinepubs/trr/1978/673/673-012.pdf), McFadden, D. (1978)\\\n[11] [Recreating passenger mode choice-sets for transport simulation: A case study of London, UK](https://www.icevirtuallibrary.com/doi/10.1680/jsmic.17.00018), Hillel, T.; Elshafie, M. Z. E. B.; Jin, Y. (2018)\\\n[12] [ResLogit: A residual neural network logit model for data-driven choice modelling](https://doi.org/10.1016/j.trc.2021.103050), Wong, M.; Farooq, B. (2021)\\\n[13] [Enhancing Discrete Choice Models with Representation Learning](https://arxiv.org/abs/1812.09747), Sifringer, B.; Lurkin, V.; Alahi, A. (2018)\\\n[14] [A Customer Choice Model with HALO Effect](https://arxiv.org/abs/1805.01603), Maragheh, R., Y.; Chronopoulou, A.; Davis, J., M. (2018)\\\n[15] [Modeling Choice via Self-Attention](https://arxiv.org/abs/2311.07607), Ko, J.; Li, A., A. (2023)\\\n[16] [SHOPPER: A Probabilistic Model of Consumer Choice with Substitutes and Complements](https://arxiv.org/abs/1711.03560), Ruiz, F. J. R.; Athey, S.; Blei, D. M. (2019)\n\n### Code and Repositories\n\n*Official models implementations:*\n\n[1] [RUMnet](https://github.com/antoinedesir/rumnet)\\\n[7] TasteNet [[Repo1](https://github.com/YafeiHan-MIT/TasteNet-MNL)] [[Repo2](https://github.com/deborahmit/TasteNet-MNL)]\\\n[12] [ResLogit](https://github.com/LiTrans/reslogit)\\\n[13] [Learning-MNL](https://github.com/BSifringer/EnhancedDCM)\\\n[16] [SHOPPER](https://github.com/franrruiz/shopper-src)\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fartefactory%2Fchoice-learn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fartefactory%2Fchoice-learn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fartefactory%2Fchoice-learn/lists"}