Disclaimer!!! Data uploaded here are collected from the internet. The sole purposes of uploading these data are to provide this Kaggle community with a good source of data for analysis and research. I don't own these datasets and am also not responsible for them legally by any means. I am not charging anything (either monetary or any favor) for this dataset.

For the first time, Nifty 50 stocks data and two indices data, along with 55 technical indicators used by Market experts are calculated and made available. Kindly download the data and make sure to share your code in public and if you like this data, do upvote. Thank you.

About Nifty 50

The NIFTY 50 index is a well-diversified 50 companies index reflecting overall market conditions. NIFTY 50 Index is computed using the free float market capitalization method.

NIFTY 50 can be used for a variety of purposes such as benchmarking fund portfolios, launching of index funds, ETFs and structured products.

Overview

This dataset contains historical daily prices for Nifty 100 stocks and indices currently trading on the Indian Stock Market. - Data samples are of 5-minute intervals and the availability of data is from Jan 2015 to Feb 2022. - Along with OHLCV (Open, High, Low, Close, and Volume) data, we have created 55 technical indicators. - More details about these technical indicators are provided in the Data description file.

Content

The whole dataset is around 33 GB (compressed here to 13 GB), and 100 stocks (Nifty 100 stocks) and 2 indices (Nifty 50 and Nifty Bank indices) are present in this dataset. Details about each file are - - OHLCV (Open, High, Low, Close, and Volume) data - 55 Technical indicator values are also present

Inspiration

• Data is uploaded for Research and Educational purposes.

Possible problem statements

• Univariate and Multi-variate time series forecasting of stock prices and index prices
• Multi-variate data can be used to predict the trend of the stock price (Buy or Sell or Hold)
• Different intraday or positional trading strategies can be built out of this multivariate data. [technical indicators are already added here]
• EDA on time series data

Stock Names

| ACC | ADANIENT | ADANIGREEN | ADANIPORTS | AMBUJACEM | | -- | -- | -- | -- | -- | | APOLLOHOSP | ASIANPAINT | AUROPHARMA | AXISBANK | BAJAJ-AUTO | | BAJAJFINSV | BAJAJHLDNG | BAJFINANCE | BANDHANBNK | BANKBARODA | | BERGEPAINT | BHARTIARTL | BIOCON | BOSCHLTD | BPCL | | BRITANNIA | CADILAHC | CHOLAFIN | CIPLA | COALINDIA | | COLPAL | DABUR | DIVISLAB | DLF | DMART | | DRREDDY | EICHERMOT | GAIL | GLAND | GODREJCP | | GRASIM | HAVELLS | HCLTECH | HDFC | HDFCAMC | | HDFCBANK | HDFCLIFE | HEROMOTOCO | HINDALCO | HINDPETRO | | HINDUNILVR | ICICIBANK | ICICIGI | ICICIPRULI | IGL | | INDIGO | INDUSINDBK | INDUSTOWER | INFY | IOC | | ITC | JINDALSTEL | JSWSTEEL | JUBLFOOD | KOTAKBANK | | LICI | LT | LTI | LUPIN | M&M | | MARICO | MARUTI | MCDOWELL-N | MUTHOOTFIN | NAUKRI | | NESTLEIND | NIFTY 50 | NIFTY BANK | NMDC | NTPC | | ONGC | PEL | PGHH | PIDILITIND | PIIND | | PNB | POWERGRID | RELIANCE | SAIL | SBICARD | | SBILIFE | SBIN | SHREECEM | SIEMENS | SUNPHARMA | | TATACONSUM | TATAMOTORS | TATASTEEL | TCS | TECHM | | TITAN | TORNTPHARM | ULTRACEMCO | UPL | VEDL | | WIPRO | YESBANK | | | |

PURPOSE (possible uses)

Non-professional investors often try to find an interesting stock among those in an index (such as the Standard and Poor's 500, Nasdaq, etc.). They need only one company, the best, and they don't want to fail (perform poorly). So, the metric to optimize is accuracy, described as:

Accuracy = True Positives / (True Positives + False Positives)

And the predictive model can be a binary classifier.

The data covers the price and volume of shares of 31 NASDAQ companies in the year 2022.

Context

Every data set I found to predict a stock price (investing) aims to find the price for the next day, and only for that stock. But in practical terms, people like to find the best stocks to buy from an index and wait a few days hoping to get an increase in the price of this investment.

Content

Rows are grouped by companies and their age (newest to oldest) on a common date. The first column is the company. The following are the age, market, date (separated by year, month, day, hour, minute), share volume, various traditional prices of that share (close, open, high...), some price and volume statistics and target. The target is mainly defined as 1 when the closing price increases by at least 5% in 5 days (open market days). The target is 0 in any other case.

Complex features and target were made by executing: https://www.kaggle.com/code/luisandresgarcia/202307

Thanks

Many thanks to everyone who participates in scientific papers and Kaggle notebooks related to financial investment.