apply(), the largest virtual ML data engineering conference, is back on Nov. 14 with speakers from Meta, Riot Games & more! Register today
Because data transformation is where it all begins
Count the number of drivers available in the given area.
Get trading statistics about the last hour of trading
PythonFinancial Market Forecasting
Get the previous day's closing price (useful for day-to-day comparisons).
SparkSQLFinancial Market Forecasting
Determine the percent of daily return from one closing price to the next closing price.
Count the number of rides recently requested in the given area.
Compute the mean and standard deviation of ride durations.
Computes the z-score of the requested ride, relative to historical rides.
Compute the Jaccard similarity between the user's search query and the candidate product title.
PythonSearch and Ranking
Determine if the candidate product is included in the user's most recent 10 product visits within the last hour.
Analyse closing prices seen over different timespans.
Analyse stock trades made each day.
Get the closing price of a stock.
Determine the popularity of a candidate product by analyzing its visit count, cart additions, and purchase frequency.
SparkSQLSearch and Ranking
Determine an applicant’s total spend across accounts in the last 30, 60, and 90 days.
Determine how recently your users have engaged with a product.
Aggregate a user’s historical interactions with all product categories.
Identify by how many standard deviations the current transaction amount deviates from the mean transaction amount for a user.
Capture a user’s previous interactions and ratings with books from the same author and category as the book currently being considered.
Retrieve a user’s latest unique distinct product ratings within the past 365 days.
Statistically capture the popularity of a product.
Examine the number of transactions made by a user at the same merchant in the 30 minutes immediately preceding the current transaction time.
Measure the degree to which a user’s recent transactions differ from their usual behavior.
Calculate the distance between the current transaction location and the user’s previous transaction location.
Unfortunately, Tecton does not currently support these clouds. We’ll make sure to let you know when this changes!
However, we are currently looking to interview members of the machine learning community to learn more about current trends.
If you’d like to participate, please book a 30-min slot with us here and we’ll send you a $50 amazon gift card in appreciation for your time after the interview.
Interested in trying Tecton? Leave us your information below and we’ll be in touch.