{"id":12,"date":"2025-08-01T21:21:55","date_gmt":"2025-08-01T21:21:55","guid":{"rendered":"http:\/\/vargas-solar.com\/seeds\/?page_id=12"},"modified":"2025-08-25T20:16:26","modified_gmt":"2025-08-25T20:16:26","slug":"hands-on","status":"publish","type":"page","link":"http:\/\/vargas-solar.com\/seeds\/hands-on\/","title":{"rendered":"HANDS-ON"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\"><strong>Case Study: NGO Recommender System for Equitable Resource Distribution<\/strong><\/h2>\n\n\n\n<p class=\"has-blue-color has-text-color has-link-color has-small-font-size wp-elements-dabf67cc82f25be018687a4ea870e1af\">&#8211; Context: humanitarian NGO serving marginalized communities<br>&#8211; Data constraints: sensitive, sovereign, possibly incomplete<br>&#8211; Model constraints: fairness-aware, energy-efficient, explainable<br>&#8211; Deployment decisions: cloud vs. edge; jurisdictional limitations<br>&#8211; Discussion on socio-technical trade-offs and ethical dilemmas<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">1. <strong>Context<\/strong><\/h3>\n\n\n\n<p>You are part of a data science team working with a&nbsp;<strong>humanitarian NGO<\/strong>&nbsp;that supports&nbsp;<strong>marginalized and underserved communities<\/strong>&nbsp;in the Global South. The organization is building a&nbsp;<strong>recommender system<\/strong>&nbsp;to suggest educational, health, and economic support services to individuals based on demographic profiles, local context, and historical access patterns.<\/p>\n\n\n\n<p>Your goal is to design and prototype a&nbsp;<strong>responsible and fair recommendation system<\/strong>&nbsp;that is technically sound while&nbsp;<strong>respecting data sovereignty, inclusivity, and environmental sustainability<\/strong>.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">2. <strong>Objectives of the Hands-On<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Build or simulate a prototype recommender using Python (scikit-learn or similar).<\/li>\n\n\n\n<li>Apply&nbsp;<strong>fairness metrics<\/strong>&nbsp;to evaluate and mitigate potential bias.<\/li>\n\n\n\n<li>Measure&nbsp;<strong>energy impact<\/strong>&nbsp;using tracking tools like&nbsp;<code>codecarbon<\/code>.<\/li>\n\n\n\n<li>Make a deployment recommendation based on&nbsp;<strong>jurisdictional, environmental, and equity trade-offs<\/strong>.<\/li>\n\n\n\n<li>Reflect on the&nbsp;<strong>ethical dilemmas<\/strong>&nbsp;and&nbsp;<strong>power dynamics<\/strong>&nbsp;embedded in your design.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">3. Considerations and constraints<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\">3.1 <strong>Data Constraints<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Sensitive<\/strong>&nbsp;data: includes ethnicity, location, health status, socio-economic indicators.<\/li>\n\n\n\n<li><strong>Sovereign<\/strong>&nbsp;data: stored on regional servers due to local or Indigenous data governance laws (e.g., OCAP, GDPR).<\/li>\n\n\n\n<li><strong>Incomplete or biased<\/strong>: certain groups (e.g., Indigenous communities, women, undocumented migrants) are underrepresented due to historical inequalities or collection barriers.<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">3.2 <strong>Model Constraints<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Must be&nbsp;<strong>fairness-aware<\/strong>: avoid reinforcing existing inequities (e.g., services only targeting urban or male populations).<\/li>\n\n\n\n<li>Must be&nbsp;<strong>energy-efficient<\/strong>: the NGO operates in low-resource settings with limited access to cloud infrastructure.<\/li>\n\n\n\n<li>Must be&nbsp;<strong>explainable<\/strong>: users and NGO staff need to understand why recommendations are made (e.g., for trust and compliance).<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">3.3 <strong>Deployment Considerations<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Cloud<\/strong>&nbsp;options may offer compute resources but violate sovereignty or sustainability goals.<\/li>\n\n\n\n<li><strong>Edge computing<\/strong>&nbsp;can reduce latency and emissions but limits model complexity.<\/li>\n\n\n\n<li><strong>Hybrid<\/strong>&nbsp;architectures (e.g., local + cloud fallback) may offer compromises but introduce complexity.<\/li>\n\n\n\n<li><strong>Jurisdictional constraints<\/strong>: hosting in EU or Africa versus U.S. (legal exposure to non-local law enforcement or surveillance).<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">4. To-Do Instructions<\/h2>\n\n\n\n<p>The general lines of the solution can be found <a href=\"https:\/\/gist.github.com\/gevargas\/6ac10adead6ed7ecdb9bf00af67ec38d\" target=\"_blank\" rel=\"noreferrer noopener\">here<\/a> <\/p>\n\n\n\n<div class=\"wp-block-group\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\">\n<ul class=\"wp-block-list\">\n<li>1.&nbsp;Data Simulation<\/li>\n\n\n\n<li>2.&nbsp;Build a Simple Recommender<\/li>\n\n\n\n<li>3.&nbsp;Evaluate Fairness<\/li>\n\n\n\n<li>4.&nbsp;Track Energy Consumption<\/li>\n\n\n\n<li>5.&nbsp;Deployment Trade-Off Matrix<\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<p class=\"has-blue-color has-text-color has-link-color wp-elements-4d38a6b290b8e86f839cdd6b734135c0\">Discuss in your group: What is the\u00a0<strong>most responsible<\/strong>\u00a0deployment strategy? We will discuss my perspective in class.<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>Criteria<\/th><th>Cloud (EU)<\/th><th>Sovereign Local<\/th><th>Edge Device<\/th><\/tr><\/thead><tbody><tr><td>Compute Power<\/td><td>High<\/td><td>Medium<\/td><td>Low<\/td><\/tr><tr><td>Legal Compliance<\/td><td>Partial<\/td><td>High<\/td><td>Medium<\/td><\/tr><tr><td>Energy Footprint<\/td><td>High<\/td><td>Medium<\/td><td>Low<\/td><\/tr><tr><td>Latency<\/td><td>High<\/td><td>Low<\/td><td>Very Low<\/td><\/tr><tr><td>Inclusivity Control<\/td><td>Low<\/td><td>High<\/td><td>High<\/td><\/tr><tr><td>Deployment Complexity<\/td><td>Medium<\/td><td>High<\/td><td>Medium<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">4. <strong>Wrap-Up Discussion Prompts<\/strong><\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>What biases emerged from the data and the model? How did you address them?<\/li>\n\n\n\n<li>How did energy tracking influence your modeling decisions?<\/li>\n\n\n\n<li>Which deployment option balances fairness, sovereignty, and sustainability?<\/li>\n\n\n\n<li>What&nbsp;<strong>epistemic or power asymmetries<\/strong>&nbsp;are still embedded in your pipeline?<\/li>\n\n\n\n<li>How would you document your decision for an ethics audit?<\/li>\n<\/ul>\n\n\n\n<p><strong>Optional Deliverables (Extension)<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Reflective mini-essay or blog post: \u201cHow can I decolonize and decarbonize my pipeline?\u201d<\/li>\n\n\n\n<li>A 1-page reflection:&nbsp;<strong>\u201cHow I balanced sovereignty, fairness, and sustainability in my design\u201d<\/strong><\/li>\n\n\n\n<li>Fairness-aware scoring prototype or resource optimization policy sketch\n<ul class=\"wp-block-list\">\n<li>A JSON or YAML model card including:<\/li>\n\n\n\n<li>Dataset description<\/li>\n\n\n\n<li>Fairness audit summary<\/li>\n\n\n\n<li>Carbon estimate<\/li>\n\n\n\n<li>Deployment recommendation<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Case Study: NGO Recommender System for Equitable Resource Distribution &ndash; Context: humanitarian NGO serving marginalized communities&ndash; Data constraints: sensitive, sovereign, possibly incomplete&ndash; Model constraints: fairness-aware, energy-efficient, explainable&ndash; Deployment decisions: cloud vs. edge; jurisdictional limitations&ndash; Discussion on socio-technical trade-offs and ethical dilemmas 1. Context You are part of a data science team working with a&nbsp;humanitarian NGO&nbsp;that [&hellip;]<\/p>\n","protected":false},"author":11,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-12","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"http:\/\/vargas-solar.com\/seeds\/wp-json\/wp\/v2\/pages\/12","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/vargas-solar.com\/seeds\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/vargas-solar.com\/seeds\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/vargas-solar.com\/seeds\/wp-json\/wp\/v2\/users\/11"}],"replies":[{"embeddable":true,"href":"http:\/\/vargas-solar.com\/seeds\/wp-json\/wp\/v2\/comments?post=12"}],"version-history":[{"count":10,"href":"http:\/\/vargas-solar.com\/seeds\/wp-json\/wp\/v2\/pages\/12\/revisions"}],"predecessor-version":[{"id":53,"href":"http:\/\/vargas-solar.com\/seeds\/wp-json\/wp\/v2\/pages\/12\/revisions\/53"}],"wp:attachment":[{"href":"http:\/\/vargas-solar.com\/seeds\/wp-json\/wp\/v2\/media?parent=12"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}