Introducing

Analyzing Market Sentiment with the Short Volume and Short Interest APIs

Jun 17, 2025

In this tutorial, we'll explore the newly released Short Volume and Short Interest APIs, which have just come out of beta. These endpoints provide two complementary views into short-selling activity, short volume captures daily short sale trading activity, while short interest reflects the total number of short positions that remain open over time. Together, they offer a view into market sentiment, trading pressure, and potential short squeeze conditions.

We'll walk through two practical examples using both APIs, retrieving daily short volume for NVDA, and analyzing short interest trends over time using real cases like the GME short squeeze.

Short Volume vs Short Interest

Since these two APIs provide complementary views into short-selling activity, it helps to understand how they differ in terms of timing, scope, and use cases. The key difference is in how frequently they update and what kind of market behavior they reflect:

• Short volume measures the number of shares sold short each day. It updates daily and is useful for tracking short-term sentiment and trading behavior.
• Short interest shows the total number of open short positions that haven’t been closed. It is reported twice per month and reflects longer-term positioning and risk.

Traders often use short volume to monitor intraday or daily shifts, while short interest is better suited for understanding broader sentiment and identifying the potential for short squeezes.

In the next section, we’ll show how to use the Short Volume API to analyze daily short-selling trends in individual stocks.

Getting Started with the Short Volume API

The Short Volume API gives you access to daily short sale data, including exempt volume breakdowns, venue-level reporting, and short volume ratios. This data can be useful for identifying short-term sentiment shifts and tracking unusual trading activity.

Here’s a simple example to fetch short volume data for Advanced Micro Devices (AMD) on October 9th, 2024:

from polygon import RESTClient

client = RESTClient("YOUR_API_KEY_HERE")

items = []
for item in client.list_short_volume(
	ticker="AMD",
	date="2024-10-09",
	):
    items.append(item)

print(items)

This script outputs the short volume data for AMD on the specified date, as shown below:

[
    ShortVolume(
        adf_short_volume=0,
        adf_short_volume_exempt=0,
        date="2024-10-07",
        exempt_volume=48277,
        nasdaq_carteret_short_volume=8835357,
        nasdaq_carteret_short_volume_exempt=34428,
        nasdaq_chicago_short_volume=138547,
        nasdaq_chicago_short_volume_exempt=0,
        non_exempt_volume=9270966,
        nyse_short_volume=345339,
        nyse_short_volume_exempt=13849,
        short_volume=9319243,
        short_volume_ratio=46.31,
        ticker="AMD",
        total_volume=20122459,
    )
]

You can also query by date range, sort by short volume ratio, or monitor daily changes to spot trends early. Next, let’s walk through a real world example using NVIDIA (NVDA) to see how short volume evolved during some recent news about large language model training.

Visualizing Short Volume: NVDA and the DeepSeek Spike

Short volume data becomes especially valuable when unexpected developments shift market sentiment. One notable example occurred around January 20th, 2025, when the release of DeepSeek, a research paper proposing a breakthrough in training large reasoning models with significantly less hardware, triggered a sharp reaction in AI and semiconductor stocks.

While some investors viewed the advance as bullish for AI efficiency, others speculated it could disrupt existing business models or reduce demand for high-end GPUs. This uncertainty led to a notable spike in short volume for NVIDIA (NVDA), as traders positioned themselves around the news.

Let’s visualize this activity to understand how short sellers responded.

from polygon import RESTClient
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
import matplotlib.dates as mdates

client = RESTClient()

def fetch_short_volume(ticker, start_date, end_date):
    data = []
    for item in client.list_short_volume(
        ticker=ticker,
        date_gte=start_date,
        date_lte=end_date,
        limit=1000,
    ):
        data.append({
            "date": item.date,
            "short_volume": item.short_volume
        })
    df = pd.DataFrame(data)
    df["date"] = pd.to_datetime(df["date"])
    return df

nvda_short_volume = fetch_short_volume("NVDA", "2024-11-01", "2025-03-01")
print(nvda_short_volume.head())

And now, let’s plot the short volume data:

def plot_short_volume(data):
    plt.figure(figsize=(10, 5))
    plt.plot(data['date'], data['short_volume'], marker='o', linestyle='-', color='red')
    plt.title('Short Volume in NVDA (Nov 2024 – Mar 2025)', fontsize=14, fontweight='bold')
    plt.xlabel('Date')
    plt.ylabel('Short Volume')
    plt.grid(True)

    plt.gca().xaxis.set_major_locator(mdates.MonthLocator())
    plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b %d'))
    plt.xticks(rotation=45)
    plt.gca().yaxis.set_major_formatter(ticker.StrMethodFormatter('{x:,.0f}'))

    plt.tight_layout()
    plt.show()

plot_short_volume(nvda_short_volume)

This data and the accompanying visualization highlights how a technical breakthrough, even a speculative one, can drive real world changes in trading behavior, making short volume a valuable tool for monitoring sentiment around key inflection points.

Getting Started with the Short Interest API

The Short Interest API gives you access to bi-monthly reported short interest data, including the total number of shares sold short but not yet covered, the average daily trading volume, and the calculated days to cover ratio. This data is useful for analyzing longer-term sentiment, risk exposure, and the potential for short squeezes.

Here’s a simple example to fetch short interest data for Advanced Micro Devices (AMD):

from polygon import RESTClient

client = RESTClient("YOUR_API_KEY_HERE")

items = []
for item in client.list_short_interest(
    ticker="AMD",
    limit=10
):
    items.append(item)

print(items)

This script returns the most recent short interest filings for AMD, including the number of shares sold short and how long it would take to cover those positions based on average volume:

[
    ShortInterest(
        avg_daily_volume=52021594,
        days_to_cover=1.0,
        settlement_date="2023-09-15",
        short_interest=30062210,
        ticker="AMD",
    )
]

Short interest is updated twice per month and reflects the broader positioning of short sellers in the market. You can use this data to monitor longer term trends in market sentiment, compare changes over time, or identify stocks that may be vulnerable to a short squeeze if buying pressure rises.

Next, we’ll walk through a historical example using GameStop (GME) to illustrate how short interest levels can foreshadow major price moves during periods of intense market pressure.

Visualizing Short Interest: The GameStop Phenomenon

One of the most dramatic examples of short positioning influencing stock prices occurred with the GameStop short squeeze in January 2021. Retail traders noticed extremely high short interest in GME and began aggressively buying shares, triggering a chain reaction that forced short sellers to cover their positions, rapidly driving the stock price higher.

Let’s use the Short Interest API to visualize how short interest in GameStop evolved leading up to and during this event.

from polygon import RESTClient
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
import matplotlib.dates as mdates

client = RESTClient()

def fetch_short_interest(ticker, start_date, end_date):
    data = []
    for item in client.list_short_interest(
        ticker=ticker,
        settlement_date_gte=start_date,
        settlement_date_lte=end_date,
        sort="settlement_date.asc",
        limit=1000,
    ):
        data.append({
            "date": item.settlement_date,
            "short_interest": item.short_interest,
            "ticker": item.ticker
        })
    df = pd.DataFrame(data)
    df["date"] = pd.to_datetime(df["date"])
    return df

# Fetch short interest data for GME
gme_short_interest = fetch_short_interest("GME", "2020-06-01", "2021-06-31")
print(gme_short_interest)

Now, let’s plot this data to visualize the trend:

def plot_short_interest(data):
    plt.figure(figsize=(10, 5))
    plt.plot(data['date'], data['short_interest'], marker='o', linestyle='-', color='red')
    plt.title('Short Interest in GME (Jun 2020 – Jun 2021)', fontsize=14, fontweight='bold')
    plt.xlabel('Date')
    plt.ylabel('Short Interest')
    plt.grid(True)

    plt.gca().xaxis.set_major_locator(mdates.MonthLocator())
    plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b %Y'))
    plt.xticks(rotation=45)
    plt.gca().yaxis.set_major_formatter(ticker.StrMethodFormatter('{x:,.0f}'))

    plt.tight_layout()
    plt.show()

plot_short_interest(gme_short_interest)

This chart highlights how short interest levels in GME remained elevated in the months leading up to January 2021, a key condition that helped fuel the short squeeze once buying pressure intensified. Then, as the short squeeze took place you can see short interest sharply declines.

Other Short Squeeze Case Studies to Explore

• AMC Entertainment (AMC) – Short squeeze from late May to early June 2021, driven by retail coordination.
• Bed Bath & Beyond (BBBY) – Squeezes in both January 2021 and August 2022 amid volatility and bankruptcy concerns.
• Tilray Inc. (TLRY) – Cannabis-sector surge in early 2021, accompanied by high short interest and speculative volume.
• Beyond Meat (BYND) – Post-IPO short activity and sharp reversals from 2019 to 2021.
• Virgin Galactic (SPCE) – Short positioning and hype around commercial space travel caused sharp price swings in mid-2021.

These examples show how elevated short interest, particularly in speculative or narrative-driven stocks, can increase the risk of violent price moves. Monitoring this data using the Short Interest API helps traders and analysts track exposure, spot rising pressure, and prepare for squeeze scenarios before they unfold.

Next Steps

In this tutorial, we explored how to use the Short Volume and Short Interest APIs to analyze short-selling activity from both daily and longer-term perspectives. We looked at how short volume can help detect shifts in sentiment or speculative spikes, as seen with NVDA and DeepSeek, and how short interest reveals broader positioning that can signal risks or opportunities, like the GameStop short squeeze.

These APIs are valuable tools for traders, analysts, and anyone looking to better understand what's happening beneath the surface of the market. Whether you're scanning for potential short squeezes, assessing bearish sentiment, or refining your risk models, short data can add another layer of insight to your decision-making.

Happy exploring!

• 

  Team Polygon

  editor

  Read More