updates

Signed-off-by: (Bit-Mage) <[email protected]>

Content/20241031150229-data_science_hierarchy_of_needs.org

@@ -7,25 +7,25 @@ From Upstream (root initiatives) to Downstream (consequent initiatives)
 
 * collect
 ** instrumentation
-** logging
-** sensors
+** [[id:665e997a-5628-4481-902c-47af4ba30336][logging]]
+** [[id:0bb707ba-24a5-44b3-8e23-45ade88f605c][sensors]]
 ** external data
 ** user generated content
 * move/store
 ** reliable data flow
-** infrastructure
+** [[id:54b9dd70-6104-4f01-8007-967b16f8e010][infrastructure]]
 ** pipelines
-** ETL
-** structured data storage
-** unstructured data storage
+** [[id:1656ed9e-9ed0-4ddb-9953-98189f6bb42e][ETL]]
+** [[id:a0cb423e-4e39-4b7c-886d-57d9796f35ed][structured data storage]]
+** [[id:64b40352-30c9-4b16-80df-2de3dd36d451][unstructured data storage]]
 * explore/transform
 ** cleaning
-** anomaly detection
+** [[id:a9f08fcf-c62d-40c0-a7fb-53d7f827b5ea][anomaly detection]]
 ** prepprocessing/preparation
 * aggregate/label
-** A/B testing
+** [[id:85ff1796-5245-4b42-8f97-64b1fc9487e0][A/B testing]]
 ** Experimentation
 ** simpler ML algorithms
 * learn/optimize
-** AI
-** Deep Learning
+** [[id:db649cb6-047e-426e-8cdc-774586ef30a0][AI]]
+** [[id:20230713T110040.814546][Deep Learning]]

Content/20241031165027-sensor.org

@@ -0,0 +1,5 @@
+:PROPERTIES:
+:ID:       0bb707ba-24a5-44b3-8e23-45ade88f605c
+:END:
+#+title: Sensor
+#+filetags: :electronics:

Content/20241031165114-structured_data_storage.org

@@ -0,0 +1,5 @@
+:PROPERTIES:
+:ID:       a0cb423e-4e39-4b7c-886d-57d9796f35ed
+:END:
+#+title: Structured data storage
+#+filetags: :data:

Content/20241031165127-unstructured_data_storage.org

@@ -0,0 +1,5 @@
+:PROPERTIES:
+:ID:       64b40352-30c9-4b16-80df-2de3dd36d451
+:END:
+#+title: Unstructured data storage
+#+filetags: :data:

Content/20241031165152-a_b_testing.org

@@ -0,0 +1,40 @@
+:PROPERTIES:
+:ID:       85ff1796-5245-4b42-8f97-64b1fc9487e0
+:END:
+#+title: A/B testing
+#+filetags: :cs:
+
+* Overview
+** *Definition*:
+  - A/B testing, also known as split testing, is a method of comparing two versions of a web page, application, or product feature to determine which one performs better in achieving a specific goal.
+
+** *Components*:
+  - *Control Group (A)*: The original version being tested.
+  - *Variant Group (B)*: The modified version where some changes have been made.
+  - *Metrics*: Quantifiable data points used to evaluate the performance, such as conversion rates, click-through rates, or user engagement metrics.
+
+** *Process*:
+  - *Hypothesis Formation*: Define what change you believe will improve the outcome.
+  - *Design*: Create alternate versions (A and B) of the element to be tested.
+  - *Randomization*: Users are randomly assigned to either version A or B to ensure fairness and reliability of the test results.
+  - *Data Collection*: Gather data on how users interact with both versions.
+  - *Analysis*: Use statistical methods to determine if the observed differences are significant.
+
+** *Statistical Significance*:
+  - This refers to the likelihood that the results of the test are not due to random chance. P-values and confidence intervals are often used to assess this.
+
+** *Tools and Software*:
+  - Common tools include Google Optimize, Optimizely, and Adobe Target, among others, which facilitate the execution and analysis of A/B tests.
+
+** *Applications*:
+  - Used extensively in web design, marketing campaigns, product development, and UX/UI design.
+
+** *Limitations*:
+  - *Sample Size Constraints*: Too small sample sizes may not yield significant results.
+  - *Time and Resources*: Testing can be time-consuming and require substantial resources.
+  - *External Validity*: Results may not always generalize beyond the specific setting or population tested.
+
+** Connections:
+- The success of A/B testing largely depends on correctly identifying impactful changes.
+- It requires a balanced approach to data collection and analysis, ensuring that randomization and statistical interpretations are executed properly.
+- Tools are integral for managing the complexity and scale of A/B tests, especially as the number of tests or user groups increases.