{"id":17133780,"url":"https://github.com/slavikdev/ml-runbook","last_synced_at":"2026-01-30T21:02:40.543Z","repository":{"id":142155528,"uuid":"288722066","full_name":"slavikdev/ml-runbook","owner":"slavikdev","description":"Collection of solutions for common ML problems","archived":false,"fork":false,"pushed_at":"2020-08-20T14:51:00.000Z","size":9,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-13T17:51:35.850Z","etag":null,"topics":["ai","cheatsheet","machine-learning","ml","runbook"],"latest_commit_sha":null,"homepage":"","language":null,"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/slavikdev.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":"2020-08-19T12:10:38.000Z","updated_at":"2020-08-20T14:51:04.000Z","dependencies_parsed_at":null,"dependency_job_id":"adc1406c-d5ea-451f-95bf-2bda34b75552","html_url":"https://github.com/slavikdev/ml-runbook","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/slavikdev/ml-runbook","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/slavikdev%2Fml-runbook","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/slavikdev%2Fml-runbook/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/slavikdev%2Fml-runbook/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/slavikdev%2Fml-runbook/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/slavikdev","download_url":"https://codeload.github.com/slavikdev/ml-runbook/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/slavikdev%2Fml-runbook/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28919362,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-30T20:25:28.696Z","status":"ssl_error","status_checked_at":"2026-01-30T20:25:13.426Z","response_time":66,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["ai","cheatsheet","machine-learning","ml","runbook"],"created_at":"2024-10-14T19:43:01.331Z","updated_at":"2026-01-30T21:02:40.526Z","avatar_url":"https://github.com/slavikdev.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# ML Runbook\n\nCollection of solutions for common ML problems. Contributions are welcome :)\n\n## Dataset\n\n### When to use a large dataset\n\n- If you have high variance (overfitting).\n- If the features are good enough for prediciton and a human expert can do manual estimation based on them.\n- If the algorithm has many parameters and can represent fairly complex functions.\n\n## High variance (overfitting)\n\nYour model is performing very well on the training set, but poorly on the test set.\n\n### In general\n\n- Try getting more training examples.\n- Try smaller set of features.\n- When using regularization, try increasing the `lambda` parameter.\n\n### SVM\n\n- Try decreasing the parameter `C` (1/lambda).\n- Try increasing the parameter `sigma^2`.\n\n## High bias (underfitting)\n\nYour model performs poorly on both training and test sets.\n\n### In general\n\n- Try adding more features features\n- Try adding polynomial features i.e. `x^2`, `x1*x2` etc.\n- When using regularization, try decreasing the `lambda` parameter.\n\n### SVM\n\n- Try increasing the parameter `C` (1/lambda).\n- Try decreasing the parameter `sigma^2`.\n\n## Choosing the right algorithm\n\n### Logistic regression vs SVM\n\n- If the number of features is large (relative to the number of examples), use either logistic regression or SVM without a kernel.\n- If the number of features is small and the number of examples is intermediate (up to 10K), use SVM with Gaussian kernel.\n- If the number of features is small, but the number of examples is large (over 10k), create/add more features, then use logistic regression or SVM without a kernel.\n\n### Anomaly detection vs supervised learning\n\nWhen to use anomaly detection algorithm (e.g. Gaussian distribution):\n\n- You expect a very small number of anomalies (up to 20) and a large number of non-anomalous examples.\n- You expect different types of anomalies and future anomalies may look like nothing you’ve seen so far.\n\nWhen to use supervised learning:\n\n- You expect a relatively large number of anomalies.\n- Future examples are likely to be similar to the ones in the training set.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fslavikdev%2Fml-runbook","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fslavikdev%2Fml-runbook","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fslavikdev%2Fml-runbook/lists"}