{"id":20463806,"url":"https://github.com/duzzisantos/software-estimation-training","last_synced_at":"2025-08-16T13:51:49.877Z","repository":{"id":262707082,"uuid":"864817389","full_name":"duzzisantos/software-estimation-training","owner":"duzzisantos","description":null,"archived":false,"fork":false,"pushed_at":"2024-11-16T19:37:08.000Z","size":49,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-03T07:57:02.639Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/duzzisantos.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,"zenodo":null}},"created_at":"2024-09-29T08:41:59.000Z","updated_at":"2024-11-16T19:37:11.000Z","dependencies_parsed_at":"2024-11-13T21:24:36.755Z","dependency_job_id":"ee163f83-441c-4136-b8db-773e91c9f185","html_url":"https://github.com/duzzisantos/software-estimation-training","commit_stats":null,"previous_names":["duzzisantos/software-estimation-training"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/duzzisantos/software-estimation-training","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/duzzisantos%2Fsoftware-estimation-training","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/duzzisantos%2Fsoftware-estimation-training/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/duzzisantos%2Fsoftware-estimation-training/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/duzzisantos%2Fsoftware-estimation-training/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/duzzisantos","download_url":"https://codeload.github.com/duzzisantos/software-estimation-training/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/duzzisantos%2Fsoftware-estimation-training/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270720365,"owners_count":24634036,"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","status":"online","status_checked_at":"2025-08-16T02:00:11.002Z","response_time":91,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2024-11-15T13:13:10.099Z","updated_at":"2025-08-16T13:51:49.828Z","avatar_url":"https://github.com/duzzisantos.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# About\n\nThis is a backend application that helps to address one of the classical problems in Information Systems: Software Project Estimation Bias. It seeks to collect data from a client application which logs in individual work logs for sub tasks that make up a bigger task.\n\nAs task/work time logs are recorded, they are passed through Machine Learning tools like TensorFlow, Numpy and Scikit-Learn which are notably applied here to perform time-series forecasts using historical work/task time logs as well as random sampling and probability distribution functions.\n\nThe trained time series data are stored as batch data, to enable client view trained data from the past - with the view of detecting anomalies or deviations in the prediction as well as investigating the causes (which might be outside of the application data's scope. Think - what if there was a layoff, or staff were stationed to other projects - thus prolonging the time required to deliver well-known tasks?). To build this data training model, the Long-Term Short-Term Memory recurrent neural network (RNN) is applied, that way we can predict long-term non-linear series.\n\nThe PERT analysis is passed through a triangular randomization function and further passed through a Monte Carlo simulation to yield numerous amounts of simulations (10000), a mean duration, standard deviation and duration commonest in the 90th percentile.\n\n## Tools used\n\n- Python\n- FastAPI\n- MongoDB\n- TensorFlow\n- Scikit-Learn\n- Pandas\n- Numpy\n- Mathplotlib\n\n## Objectives\n\n- To generate experimental data for a research paper addressing the issue of software project time estimation bias.\n- To compare previous academic research outcomes on this topic -\n  using results generated from this system.\n- To have a system that guides developers and project managers toward making more-informed, objective decisions with regards to estimating effort and time expended in building software.\n\n## Process flow\n\nSee flow chart here:\nhttps://ibb.co/XpNCg7Q\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fduzzisantos%2Fsoftware-estimation-training","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fduzzisantos%2Fsoftware-estimation-training","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fduzzisantos%2Fsoftware-estimation-training/lists"}