Canvas & Ratio
Choose your destination platform format
Layout Template
Choose a content structure for your slides
Preset Themes
Typography & Sizing
Brand Kit Customization
AGENCYConfigure brand assets for headers & footers
Outro Slide CTA
Customize your closing call-to-action slide
Background Pattern
Build Your Carousel
Drag and drop any post card below onto a slide, or use the quick buttons to insert content/images instantly!
Understanding probability is essential in data science. In 4 minutes, I'll demolish your confusion. Let's go!
1. Statistical Distributions: There are 100s of distributions to choose from when modeling data. Choices seem endless. Use this as a guide to simplify the choice.
2. Discrete Distributions: Discrete distributions are used when the data can take on only specific, distinct values. These values are often integers, like the number of sales calls made or the number of customers that converted.
3. Continuous distributions: Used for data that can take on any value within a range or interval. These values are typically real numbers, like the percentage of visitors that converted or the forecasted revenue over the next 6 months.
4. Probability Mass Function (Discrete): Discrete distributions are described by a probability mass function, which gives the probability that a discrete random variable is exactly equal to some value. In a graph, a discrete distribution is often represented by a series of bars, where each bar represents the probability of each discrete outcome.
5. Probability Density Function (Continuous): Continuous distributions are described by a probability density function. The probability of the variable falling within a particular range is given by the area under the curve of the PDF within that range. In a graph, a continuous distribution is usually represented by a smooth curve.
6. Parametric Models: Many models assume a specific distribution. - Linear Regression: Assumes normally distributed errors. - Logistic Regression: Assumes a binomial distribution of the response variable.
7. Non-Parametric Models: These models do not make strong assumptions about the form of the data distribution. - Decision Trees - K-Nearest Neighbors - Support Vector Machines
8. Loss Functions: Distributions will come up in Loss Functions in Machine Learning (e.g. XGBoost, LightGBM, CatBoost). Selecting the right Loss Function can often improve performance. Examples: - Poisson is used for count data. - Tweedie for mixed continuous data with many zeros like intermittent demand forecasting problems.
One more thing before you go. A new problem has surfaced -- Companies NOW want AI. Yet 99% of data scientists are ignoring it. That's a huge advantage to you. I'd like to help.
On Wednesday, June 21st, I'm sharing one of my best AI Projects: How I built an AI Customer Segmentation Agent with Python: Register here (limit 500 seats): <a target="_blank" href="https://learn.business-science.io/ai-register" color="blue">learn.business-science.io/ai-register</a>
That's a wrap! Over the next 24 days, I'm sharing the 24 concepts that helped me become an AI data scientist. If you enjoyed this thread: 1. Follow me @mdancho84 for more of these 2. RT the tweet below to share this thread with your audience <a target="_blank" href="https://twitter.com/815555071517872128/status/1934210887260282916" color="blue">x.com/81555507151787…</a>