{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/you-do-not-need-a-bigger-boat-recommendations","title":"You Do Not Need a Bigger Boat: Recommendations at Reasonable Scale in a (Mostly) Serverless and Open Stack","arxiv_id":"2107.07346","date":"2021-07-15","proceeding":null,"authors":["Jacopo Tagliabue"],"abstract":"We argue that immature data pipelines are preventing a large portion of industry practitioners from leveraging the latest research on recommender systems. We propose our template data stack for machine learning at \"reasonable scale\", and show how many challenges are solved by embracing a serverless paradigm. Leveraging our experience, we detail how modern open source can provide a pipeline processing terabytes of data with limited infrastructure work.","url_abs":"https://arxiv.org/abs/2107.07346v1","url_pdf":"https://arxiv.org/pdf/2107.07346v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"you-do-not-need-a-bigger-boat-recommendations","repo_url":"https://github.com/jacopotagliabue/metaflow-intent-prediction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"you-do-not-need-a-bigger-boat-recommendations","repo_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.07346","atlas_url":"https://app.syntology.ai/?focus=2107.07346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07346"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jacopotagliabue/metaflow-intent-prediction","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":11,"unverified":3},"by_repo_kind":{"listed":{"samples":14,"ran":11,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"11789a38a836540b","entry":"enable_decorator","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/custom_decorators.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/custom_decorators.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"11789a38a836540b"}},{"code_sha256_prefix":"5513291663ef8a28","entry":"get_filename","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/utils.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5513291663ef8a28"}},{"code_sha256_prefix":"9011d0930fb34a77","entry":"make_predictions","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"remote_flow/metaflow/model.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/remote_flow/metaflow/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9011d0930fb34a77"}},{"code_sha256_prefix":"a3ce5ce1f92ca929","entry":"pip","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/custom_decorators.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/custom_decorators.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3ce5ce1f92ca929"}},{"code_sha256_prefix":"ec5dcfa1a6b0f7af","entry":"prepare_dataset","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/prepare_dataset.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/prepare_dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec5dcfa1a6b0f7af"}},{"code_sha256_prefix":"07d49ac126d9b329","entry":"read_sessions_from_training_file","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/prepare_dataset.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/prepare_dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"07d49ac126d9b329"}},{"code_sha256_prefix":"27a270038cf86be3","entry":"return_json_file_content","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/utils.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"27a270038cf86be3"}},{"code_sha256_prefix":"8f067378d424cbda","entry":"session_indexed","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"remote_flow/metaflow/model.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/remote_flow/metaflow/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f067378d424cbda"}},{"code_sha256_prefix":"3fe47de83b48302e","entry":"session_indexed","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/prepare_dataset.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/prepare_dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3fe47de83b48302e"}},{"code_sha256_prefix":"b8bb11c469473bde","entry":"tf_model_to_tar","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/deploy_model.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/deploy_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8bb11c469473bde"}},{"code_sha256_prefix":"2f93893e818afaa6","entry":"train_lstm_model","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/model.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f93893e818afaa6"}},{"code_sha256_prefix":"1ba74f174fd45278","entry":"process_raw_data","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/process_raw_data.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/process_raw_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ba74f174fd45278"}},{"code_sha256_prefix":"2c7fed7654dbad7e","entry":"read_from_parquet","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/process_raw_data.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/process_raw_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c7fed7654dbad7e"}},{"code_sha256_prefix":"17172882ad3ab9e8","entry":"return_df","repo":"jacopotagliabue/you-dont-need-a-bigger-boat","repo_kind":"listed","path":"local_flow/intent/src/process_raw_data.py","file_url":"https://github.com/jacopotagliabue/you-dont-need-a-bigger-boat/blob/HEAD/local_flow/intent/src/process_raw_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"17172882ad3ab9e8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}