{"id":22026559,"url":"https://github.com/achint08/tech-diffusion","last_synced_at":"2026-02-15T05:31:17.344Z","repository":{"id":127424005,"uuid":"485264670","full_name":"Achint08/tech-diffusion","owner":"Achint08","description":"Patents data analysis on PySpark","archived":false,"fork":false,"pushed_at":"2022-05-28T00:32:58.000Z","size":625,"stargazers_count":2,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-10-04T00:31:18.682Z","etag":null,"topics":["bert","big-data","bigquery","google-patents-dataset","machine-learning","nlp","pagera","patents-analysis","pyspark"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Achint08.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-04-25T07:23:44.000Z","updated_at":"2024-09-29T05:29:09.000Z","dependencies_parsed_at":null,"dependency_job_id":"415d9c04-1b0c-42cb-bcca-fd95e851aa45","html_url":"https://github.com/Achint08/tech-diffusion","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Achint08/tech-diffusion","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Achint08%2Ftech-diffusion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Achint08%2Ftech-diffusion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Achint08%2Ftech-diffusion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Achint08%2Ftech-diffusion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Achint08","download_url":"https://codeload.github.com/Achint08/tech-diffusion/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Achint08%2Ftech-diffusion/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29470601,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-15T05:26:30.465Z","status":"ssl_error","status_checked_at":"2026-02-15T05:26:21.858Z","response_time":118,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["bert","big-data","bigquery","google-patents-dataset","machine-learning","nlp","pagera","patents-analysis","pyspark"],"created_at":"2024-11-30T07:28:20.619Z","updated_at":"2026-02-15T05:31:17.326Z","avatar_url":"https://github.com/Achint08.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# patents-analysis\n\nIn this project, we are trying to analyze Technology diffusion using big data on Pyspark. \n\nIn simple terms, we are trying to analyze how companies/organizations depend on each other using patents dataset and their records of citations.\n\nThe module consists of the following:\n\n1. General analysis of dataset, like top 10 cited companies, top 10 patents producing companies.\n2. Graph analysis - Pagerank, Strongly connected components.\n3. Text analysis of patents abstract - LDA model\n4. Machine learning model to predict whether company A will cite company B's patent - BERT, Naive Bayes, Multilayer Perceptron, Random Forest.\n\nNote - We are only analyzing top 100 companies for each year.\n\n## What is Technology Diffusion?\n\n* The way by which innovation is disseminated through certain channels over time among the organizations.\n* Citations provide useful insight for technology dissemination processes, as patents are an important medium of invention.\n* Relation between innovation happening in organizations and how they are inter-dependent.\n\n## Dataset \u0026 Infrastructure\n\nThe dataset used is Google Patents dataset.\n\n* Platform - GCP\n* 1 master, 3 worker nodes\n* standard-m1 instance\n* 30 GB Memory\n* 8 CPU cores\n* Dataset size – 20 million rows (patents from 1976)\n* Tables -\n  * Patent\n  * Patent citation\n  * Assignee\n\n\n## Predictions\n\n* Naïve Bayes – Accuracy about 57%\n* Multilayer Perceptron – Accuracy about 98%\n* Decision Tree – Accuracy about 93%\n* Random Forest – Accuracy about 95%\n\n\n## Other Contributors\n\n- Simron Waskar\n- Sumit Dhundiyal\n- Zexu Li \n\n\n## Conclusion\n\n* Technology diffusion exists and has been increasing year by year.\n* IBM \u0026 Samsung are the top most innovation hub in the last decade.\n* We can predict the citation by an organization with certain accuracy for top 100 companies.\n* The topics extracted from documents show that technology trends are highly reflected in the abstracts/titles.\n\n## Thank you. :)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fachint08%2Ftech-diffusion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fachint08%2Ftech-diffusion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fachint08%2Ftech-diffusion/lists"}