Up until now, in my ML real estate project, I gathered data for 100 apartments. I collected the price and the size, and I allocated 70 percent of the data for training and the remaining 30 percent for testing (prediction). I know it's still not enough data, but compared to my last update on the project, it's looking better. The model is predicting the prices more accurately. I believe this improvement is mainly due to adding more data. That's it for now—you can see the results in the two pictures. I will add more data and parameters along the way. Have a great day! Guy

Starting to visualize my machine learning project. Currently, I’m using linear regression. I’m aware that it may not be the best algorithm to use, but it’s good enough for starting and experimenting

I started experimenting with the real estate ML project. It's just the baby steps, but as you can see, the first prediction (in blue) is incorrect since it has a negative value. However, after performing cost calculations and adjusting to find the right values for w and b, you can see that the prediction is much better. By the way, the prices are in millions, and this is real data from my hometown. Although it's just 3 sets of data, it's a great experiment!

What is Unsupervised Learning? Unsupervised learning is a type of machine learning where the algorithm is given data without labeled responses. Unlike supervised learning, where machines are provided with input-output pairs, unsupervised learning algorithms must identify inherent structures in the unlabelled data on their own. A common analogy to understand this is imagining a student who is given a textbook and asked to find interesting topics without being told what those topics are in advance. The student's job is to read through, identify and categorize notable themes, essentially discovering the patterns hidden within the text. Clustering: Finding Patterns in Unlabeled Data One of the most prominent techniques in unsupervised learning is clustering. Clustering involves organizing data into groups, or "clusters," where data points within the same group exhibit similar characteristics compared to those in other groups. This method is incredibly useful in a range of applications from market research to image segmentation, and much more. How Clustering Works The idea behind clustering can be visualized through the following steps: Initialization: The algorithm begins by initializing some random points as the initial 'centroids' of clusters. Assignment: Each data point is then assigned to the nearest centroid, forming a cluster. Update: The centroid of each cluster is recalculated based on the current members of the cluster. Iteration: Steps 2 and 3 are repeated until the centroids no longer move significantly, indicating that the algorithm has converged on a solution. Real-World Applications Customer Segmentation: Businesses use clustering to segment their customers into groups with similar purchasing behaviors, helping them tailor marketing strategies more effectively. Anomaly Detection: In cybersecurity, clustering can help identify unusual patterns that may indicate fraudulent activity or network intrusions. Image Analysis: By clustering pixels, algorithms can distinguish between different objects in an image, aiding in image recognition tasks and medical diagnoses.

Hi everyone, I am Shubham, a full-stack engineer from India. I am curious about engineering, business, SaaS, and connecting with like-minded people from around the world to learn more about their cultures and perspectives. I would be happy to connect with you all. Linkedin: https://www.linkedin.com/in/a-shubham-verma/ Twitter: https://x.com/npm_shubham