your market intelligence analyst
Search Results
Edit Save
3,680 results
Towards Data Science 06/18/2019 15:29
Imagine only ever being able to do anything based on a set of written instructions from someone you don’t know. Life would suck. But life doesn’t suck (or maybe it does, in which case, same) because we have the power of these super underrated things called our senses. See, as humans, we’ve evolved in extremely complex environments that constantly force us to take in a lot of information and make sense of a lot of information.
Towards Data Science 06/18/2019 14:34
A random session at the Roulette table — with Pandas and Altair. Recently I went to a casino for some fun and I was curious enough to figure out what my chances are of winning, and how long would I last at the casino given a budget, a standard betting sum, and a betting strategy to follow. So I decided to quickly write up some code to visualize a random session to the Roulette table.
Towards Data Science 06/18/2019 14:34
Today we are going to create an ML model that forecasts the price movement in the order book. This article contains a full-cycle of research: getting data, visualization, feature engineering, modeling, fine-tuning of the algorithm, quality estimation, and so on. What is an Order Book? An order book is an electronic list of buy and sell orders for a specific security or financial instrument organized by price level. An order book lists the number of shares being bid or offered at each price point, or market depth. Market depth data helps traders determine where the price of a particular security could be heading. For example, a trader may use market depth data to understand the bid-ask spread for a security, along with the volume accumulatin.
Towards Data Science 06/18/2019 14:34
Diving into DALI: How to Use NVIDIA’s GPU-Optimized Image Augmentation Library. Salvador Dalí. The Persistence of Memory. Credit: The Museum of Modern Art. Deep learning image augmentation pipelines typically offer speed or flexibility, but never both at the same time. Computationally efficient, production-ready computer vision pipelines tend to be written in C++ and require developers to specify all the nuts and bolts of image transform algorithms to such an extent that these pipelines end up not terribly amenable to further on-the-fly tweaking. On the other end of the spectrum, popular Python libraries like Pillow offer high-level APIs that let practitioners choose from seemingly unlimited combinations of tweaks that can be applied to a vas.
Towards Data Science 06/18/2019 14:33
Calculating R-squared from scratch. Source of image: link. R-squared can be abstruse to students learning data-science. Instead of introducing the mathematical formulas involved, I thought it may be refreshing to show how it’s intuitively calculated from scratch and explain each step in plain English. I’m going for a cooking-show theme here. Ingredients:. Dataset which contains at least 1 serving of independent variable (X) and exactly 1 serving of dependent variable (Y). Drizzle a linear regression line on top of the data. Drizzle a horizontal line of the average Y on the data. Python, another software, or even just a pen and paper. Dataset and Linear Regression. X , in this example, will be integers from 0–9; Y will be the first 10 digits of
Towards Data Science 06/18/2019 13:01
Do it right from the start! [Framework]. © Blake / Adobe Stock. We’re witnessing an explosion of demand for the data scientist — “the sexiest [and most hyped] job of the 21st century” . Colleges are quickly creating data science programs. Students are rushing to enroll. Executives — constantly hearing about how data science is transforming business — suffer acute FOMO. And amid the explosion lies the damage of dashed dreams of teams adrift without any plans for success. This is how to do it right from the start. “Be quick but don’t hurry.” — John Wooden. Just hoping that your new data scientists will unlock insights out of your treasure trove of data is unrealistic. The odds of failure are shockingly high — industry experts believe that only 1.
Towards Data Science 06/18/2019 09:17
What do the most funded startups have in common? (Source: Salesforce). || INTRODUCTION ||. The world of startups is a dynamic place — for entrepreneurs, there is seldom any promise of vested interest or reward once they hit the ground running. Private equity and venture capital firms enjoy a hefty profit because they are supposedly good at identifying which startups sizzle and which ones fizzle, but is there a way to automate the process? My goal was to build a model to answer the question of:. Can a computer model how much funding a startup should receive? || THE DATA ||. The data used for this article was obtained through PitchBook, one of the best sources for research and financial information on startups and the realm of private investment.
Towards Data Science 06/18/2019 09:17
Not good. For every triumphant result in machine learning, there are hundreds of buggy models that just won’t converge. Skyrocketing loss functions. Unusual validation loss. Suspiciously low training loss. All of these indicate that something is wrong. There are some beautiful references that can help thoroughly diagnose the issue, but here are the three candidates that immediately come to mind and constantly pop up. Note: This especially applies to image-oriented tasks but still has great value for general ML tasks. 1. Tinker With # of Channels. Feature maps are the number of channels in a convolutional layer, and appear in all sorts of applications. This will change the number of kernels used in a single layer. Having too many feature maps.

Financial Services

Business Issues

Companies - Public

Companies - Venture Funded

Financial Results

Global Markets

Global Risk Factors

Government Agencies

Information Technologies

Job Titles

Legal and Regulatory

Political Entities


Strategic Scenarios



  • Actions
    • Bookmark and Share: Allows you to Bookmark the page for easy future retrieval and sharing with colleagues
    • Email: Opens a pop-up window where you can write a message to the recipient of the email
    • Copy URL: Copies the URL of the requested document for pasting in an email or other document
    • Previous Versions: Only shown if essentially the same document has been republished
  • Saved Searches and Alerts
    • Save your search for later viewing & updates by clicking the blue "Save" button to the right of the search box. 

Click here for more info on Search Results.