Nishant Patel
Senior Machine Learning Scientist @Decklar
Signup · Get unlimited contacts
WORK HISTORY
Senior Machine Learning Scientist @Decklar
Created/Trained GeoSpatial Transformer model (pytorch) on geographical modality to improve accuracy in sporadic-gps connectivity cases.• Created Prediction system to estimate arrival times for multimodal shipments. Led and developed most components of the system which comprised of: • Built Custom Clustering tech to identify locations (dbscan, and custom variants of it to stop chain reaction/cluster expansion based on sensor dwell time strength and other domain features to better discover target locations automatically) • Graph/Networkx+Custom Algo to identify routes between shipment locations and using it to forecast future paths based on past preference+distance hybrid heuristicBoosted Trees (lightgbm) with domain+auto-discovered cluster features to predict dwell times at locations. • Recurrent Neural Networks(RNN)/Transformers to predict transition times Well engineering architecture to allow multiple parts of the system to swap in with various models (e.g. swapping Dwell predictor with statistical predictor when we have low amount of data) • Custom crowdsource/3rd party integrate to assimilate output of Ocean+Air legs/schedules into the overall prediction framework.• Created supply chain loops identification system. • Created custom algorithm to Identify repeating trips of Assets through various POIs • Example Loop: Discovery of container type asset’s movement through retail locations to Analyze and Predict Turn Around Time (TAT)• Created ETL Data Pipelines using Apache Beam (Python SDK) & Apache Flink which used custom processing steps. •Used ElasticSearch, Mysql, Cassandra, and Snowflake to assimilate and process various data about IOT Sensors + Assets + Shipments. Iceberg source and sink for next generation of analytical warehouse •Created an advanced pipeline to merge data from multiple sources and apply clustering to discover location and use discovered locations to further discover visitation loops.
EDUCATION
The Maharaja Sayajirao University of Baroda
MCA, Computer Software Engineering
The Maharaja Sayajirao University of Baroda
BCA, Computer Software and Web Applications
SKILLS
ABOUT NISHANT PATEL
Focused on Solving ProblemsHaving worked in fast paced product based startups; I\'ve harnessed my problem solving skills while staying unphased by ever revealing tree of sub-problems as they emerge. Focused on delivering quality productsAs the projects I worked on were directly used by customers; I know the stakes at hand and the importance of delivering quality product, which means putting in place proper metrics, logs, notifiers, with intent being: we should be the ones getting notified of the bug/problem before the customer. Focused on InnovatingWhen Ingenuity and sound fundamental knowledge get used repeatedly to a problem, they bound to get solved sooner or later if we persevere. Over the years I\'ve gone beyond the expectations and delivered novel solutions. Focused on Delivering/ProductisingOne of the hardest parts about any analytics/machine learning projects is to make it into a product from a mere POC. I\'ve learned through experience, the ways to expedite productisation.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.