Data Con LA 2021
| title | author | length |
|---|---|---|
| Data Con LA 2021 - Mayor of Los Angeles Eric Garcetti Keynote | Eric Garcetti | 01m |
Historical examples link bookkeeping and cholera mapping to modern public health and civic apps and then lists concrete city tools: CleanStat map that measures… | ||
| Keynotes 09/17/2021 | Subash DSouza, Ron Galperin, Karen Borchgrevink, Gil Elbaz, Alison Burnham, Eric Garcetti | 55m |
City government publishes a virtual checkbook with every payment for the last ten years and live dashboards including a COVID-19 spending tracker for over $1… | ||
| Keynotes 09/18/2021 | Eric Garcetti, Francesca Lazzeri, Nithya Ramanathan, Nathan Janos, Mike Burkes, Davor Bonaci | 01h 06m |
A sequence of short keynotes connects public service and product lessons: city data directs vaccine and testing placement and 1 in 10 babies have vaccine… | ||
| Keynotes 09/19/2021 | Chris Fregly, Jyothi Pradhan, Mike Swinson, Harrison Tang, Eric Weber | 01h 17m |
Five short, concrete briefings: quantum claims that 6000 clean qubits (≈1M noisy) are needed to break RSA, current devices sit at 50–200 noisy qubits, error… | ||
| Data-Driven Innovation in the Federal Government. | Kristen Honey | 43m |
InnovationX pivots HHS data into action by moving high-value datasets from DoD, DOE, HHS and VA onto Oak Ridge supercomputers, then launching HHS Protect… | ||
| Demystifying the art of Business Intelligence and Data Analytics | Brandon Wong | 39m |
Covers concrete BI workflows: SQL backend with Microsoft Dynamics, SQL Management Studio, Power BI Desktop and Report Builder, plus Azure/Hadoop, blob storage… | ||
| Effective use of big data analytics and its impact on business performance | Alfonso Berumen | 45m |
Survey of 300 SME responses across the US links a measured data analytics capability to perceptual business value with beta=0.672 and R²=45%. A capability… | ||
| Trust No One | Eysha Shirrine Powers, Eysha Sherine Powers | 40m |
Claim: fully homomorphic encryption lets external services run ML and search while data never leaves ciphertext. Demonstration uses the IBM FHE toolkit… | ||
| Using Data to Identify Needs of Foster-Care Youth | Priscila Baddouh | 43m |
Survey of 27,000 respondents ages 14–27 identifies high food, financial and housing insecurity, especially after aging out; analysis uses Python to parse open… | ||
| Using Streaming Data Pipelines in the Cloud to Achieve Success | John Lavoie | 39m |
Optum Care builds a cloud streaming pipeline that ingests databases via Kafka Connect (Debezium/JDBC), uses Avro + Confluent Schema Registry and producer… | ||
| Using Reproducible Experiments To Create Better Models | Milecia McGregor | 38m |
Demonstrates using DVC to make hyperparameter sweeps reproducible by versioning code, data and params and running queued experiments with DVC exp run against a… | ||
| What data and design can learn from each other | Alison M. Bunce | 43m |
Argues that data awareness — treating design thinking and the scientific method as equal — prevents wasted wrangling and produces clearer products. Shows a… | ||
| Unleashing the serverless data pipelines | Sunita Koppar | 38m |
Compares three architectures—Talend on Hadoop, Spark on EMR with Airflow, and AWS Glue ETL—and chooses Glue after modeling reduced input (rolled to five‑minute… | ||
| Too Much Drama and Horror Already: The COVID-19 Pandemic's Effects | Danny Kim | 34m |
Analysis of TV Time app data from about 230,000 users compares two-month pre‑WHO-declaration, early‑pandemic and “new normal” windows with seasonality adjusted… | ||
| State of MySQL Security in 2021 | Peter Zaitsev | 41m |
MySQL 8.0 is the baseline for 2021 security with concrete features: roles support for simpler privilege management, dynamic privileges to avoid excessive SUPER… | ||
| Sparse models are fast models: Improving DNN inference performance by over 10X | Lawrence Spracklen | 40m |
Sparse DNNs trade most weights for zeros and use techniques like gradual magnitude pruning, block/partition constraints and complementary sparsity to make… | ||
| Spark challenges | Vitaly Polonetsky | 31m |
ZipRecruiter migrates pipelines to Apache Spark running Spark on Kubernetes on AWS and repeatedly fixes failures by blindly increasing memory until joins and… | ||
| Develop Big Business with GOAL: Growth Opportunities & Actualization Lifecycle. | Jeff Bertman | 47m |
A repeatable GOAL methodology is presented: brainstorm into a landscape, trim to an MVU (minimum viable understanding), build via agile roadmaps, and sustain… | ||
| Scaling sentiment: Using digital surveys to geotarget vaccine distribution | JP Petrucione, Shawn Zargham | 41m |
California deploys surveys on 12 state websites and collects 90,000 responses (including ~80,000 open text answers) then uses SurveyMonkey, Google… | ||
| Operationalizing predictive analytics for homelessness prevention in Los Angeles | Brian Blackwell | 42m |
LA County pilots a Homelessness Prevention Unit that uses machine learning on de‑identified CIO InfoHub records from nine agencies to generate risk lists… | ||
| Quantum Computing: The next new technology in computing | Mark Jackson | 28m |
Quantum hardware already exists and shows concrete milestones: Google demonstrates quantum supremacy, IBM and Honeywell report rapidly rising quantum volume… | ||
| Database DevOps with Containers | Rob Richardson | 39m |
Builds an automated pipeline that takes a nightly production backup, runs a SQL script to anonymize sanitize shrink data (emails become… | ||
| ABC Of Product Strategy | Alex Alwan | 40m |
Argues that product strategy is an ongoing process that connects vision to product, not just a roadmap item, and that it belongs between product management and… | ||
| How to get real-time insights from your JSON data? | Idris Motiwala, Ian Maxon | 38m |
Couchbase Analytics runs real-time queries against native JSON with no ETL real-time JSON analytics, creating read-only shadow copies to isolate operational… | ||
| Enjoy The Air | Keerthi Gopalakrishnan | 39m |
ETA runs Glasgow trials claiming 40% choose trip mode same day and that individual transport choices drive roughly 40% of UK GHG. The team merges air sensors… | ||
| How to extract longitudinal trends of a brick-and-mortar brand's foot traffic | Avinash Gundapaneni | 40m |
Built a Macro Model that strips technology and panel-change noise from app-derived foot-traffic, using a proprietary panel of 2 million users and ~600 million… | ||
| Cloud Native and Headless BI is Here to Usher in the Future of Data Analytics | Roman Stanek | 40m |
Claims that a cloud-native, API-first “headless BI” creates a single source of metrics that serves Tableau/Power BI/Excel, data science notebooks and embedded… | ||
| Engineering a Consent Sandbox to Eliminate Annoying Pop-Ups and Dark Patterns | Ben Brook | 25m |
Explains a concrete engineering path: tried sandboxed iframes (too slow), dynamic CSPs (blocks but can’t replay), then built a runtime firewall that patches… | ||
| Building Production Data Pipelines by using TDD and Pair Programming | Cahlen Humphreys, David S. Miller | 40m |
Live demo builds a Spring Cloud Stream processor that consumes from Azure Event Hubs input, calls Azure Translate, and produces to an output topic; development… | ||
| Cryptographic speed, reliability & security | Ian Searle | 41m |
Claims a lightweight, optimized symmetric cryptosystem with variable, quantum-safe 512-bit strength (vs AES/ChaCha 256-bit), and shows it encrypts streaming… | ||
| A Layered Approach to Data Management | Jerry Power | 39m |
Argues that treating IoT as layered services avoids silos and enables reuse: a separate schema interpreter maps raw device feeds into a database, a governance… | ||
| Alice in the world of machine learning | Roksolana Diachuk | 41m |
Builds a Kubeflow proof of concept on Google Cloud that containers three components and runs them via Argo-backed pipelines: Kubeflow on GCP, Dockerized… | ||
| AI-Assisted Media Planning | Param Dhillon, Vasily Grigorovsky | 24m |
A deployed booking tool automates linear and streaming TV buys and embeds machine learning to predict efficiency and availability. Cost-per-visitor is modeled… | ||
| Keeping pace with data infrastructure so it doesn't outrun you | Francisco Javier Arceo | 38m |
Advocates embedding a software development lifecycle into data work, treating models as code with versioning, unit tests for table creation, and automated… | ||
| The balance between data privacy and user experience | Sky Cassidy | 37m |
Claim: you don't own your data but companies own the data they gather and must balance usefulness with ethics. Covers GDPR, CAN-SPAM, CCPA, CASL, social media… | ||
| Build your own social media analytics with Apache Kafka | Jakub Scholz | 38m |
Shows a working pipeline that pulls tweets via the Twitter timeline connector and a search source, ingests them with Kafka Connect, and processes them with… | ||
| Bringing data science into blockchain | Shae Wang | 44m |
Concrete metrics and pipelines get recommended: compute total transfer volume (native token and USD), transaction count, active/new address growth, and… | ||
| A Case Study - Data Movement and Transformation using Azure Data Factory | ALPA BUDDHABHATTI | 41m |
Case study builds a parameterized Azure pipeline that moves files from Blob Storage into ADLS Gen2 and runs transformations, using Azure Data Factory linked… | ||
| Deploying your model to mobile app: Offline or Online? | Bunmi Akinremi | 33m |
Shows a real fraud detection model at about 84% accuracy deployed as an online API using Flask-style tooling and cloud hosting, and contrasts that with… | ||
| Data Equity and Ethics: From Idea to Practice | Cindy Lin | 40m |
Company runs a 7-person pilot with 30 minutes of prework and one-hour workshops, then scales to six team workshops across a ~50-person org; concrete changes… | ||
| BI DataOps Development Process | Wenyang Hu, Gupta Lakkimsetti, Mary Simeon | 38m |
Describes a CSU DataOps pipeline that ingests PeopleSoft/oracle and CSV into parquet storage on S3, transforms with EMR + PySpark processing using a shared… | ||
| Personalized By Design: How to unlock long term customer value with data | Raleigh Tomlinson | 41m |
Focuses on designing data-driven personalization for Headspace membership and scaling to 100 million users, arguing that recommendations must deliver… | ||
| Building Features and Machine Learning Models for Audio Signals | Jyotika Singh | 40m |
Python library pi_audio_processing provides MFCC and GFCC extraction plus spectral and chroma features, end-to-end cleaning (low-activity removal, spectral… | ||
| Measuring the Moving Parts of User Experience in Java/.NET applications | Wendy Howard | 41m |
Demo shows a working full‑stack APM: browser RUM uses bytecode tagging to follow users, server-side BTM instruments Java by dropping a war file onto WebLogic… | ||
| Building a data infrastructure for large municipal government | Terence Davis | 42m |
County builds InfoHub that already combines about 1.7 billion rows across ~40 tables from 10 departments, producing ~2.25 million households served monthly and… | ||
| Agile Scrum Overview | Sonia Macias | 39m |
Covers Agile values and the Scrum framework with concrete practices: product backlog → sprint backlog → increment, roles as Product Owner/Developers/Scrum… | ||
| Enabling simple ML ops at Stitch Fix | Elijah ben Izzy | 40m |
Stitch Fix builds a configuration-driven ML platform that turns a serialized model plus metadata into deployable services and jobs, used by 145+ data… | ||
| Crime in the Pandemic A look at changes in Los Angeles crime during Covid-19 | Preet Singh | 38m |
Los Angeles open data from 2010–Aug 2021 and scientific Python/Jupyter + time‑series ML (including triple exponential smoothing) show overall reported crime… | ||
| Structured Data in 2021 and Beyond | Joe Devon, Denny Vrandečić, Heather Hedden, Karen Lopez | 01h 24m |
Overview of concrete tools and results: RDF/OWL and SKOS power taxonomy and ontology work, PoolParty is used to manage taxonomies and spin up graph DBs, and… | ||
| Startup Showcase | bob neustadt | 01h 09m |
Transform Max promises 40% energy reduction on rail traction transformers using edge sensors, cloud analytics and AI that predicts failures hours ahead and is… | ||
| Show, Don’t Tell How Data Is Changing Hollywood | Alex Freund, Eric Wilker, Laura Schaeffer, Michael Lofaso, Chris Detert | 01h 29m |
Panel shows concrete shifts: teams pair IBM Watson psychographic scoring with influencer inventories, yielding 1–100 personality indices; one firm says it… | ||
| A Step Towards Normalcy Beyond COVID 19 Moratorium Lift | Vishrut Chokshi, Neil Parekh | 31m |
A six-week program builds a Customer Analytic Record and a segmentation that uses ten engineered features to split the customer base into four segments… | ||
| Building data driven solutions for COVID 19 Contact Tracing & Vaccine Management | Max Bigot, Ajali Sen | 42m |
Built an AWS platform with Salesforce integration and Tableau dashboards that supports a 58‑county contact tracing program and vaccine allocation, handling 48… | ||
| Real world data & analytics journeys | Samta Kapoor, Jennifer C. Womack, Shaena Walker, Thomas P. Hobbib | 38m |
Utilities combine lidar helicopter methane surveys, stationary sensors and manual leak checks into a single asset-linked pipeline; electric teams process… | ||
| Using web data for a better tomorrow | Keren Pakes, Asaf Dekel | 41m |
Bright Data runs the Bright Initiative providing automated data collection tools to 148 partner organizations (90+ academic institutions) and claims concrete… | ||
| Public Health Innovations for COVID Response | Rebecca Friedman, Praneet Raj, Spencer Steed, Chelsea Foo, Korey Edwards | 58m |
Los Angeles County automates COVID interview entry using UiPath RPA, cutting a 120,000+ interview backlog to zero, processing over 500,000 transactions… | ||
| Exposing human trafficking networks with AI | Monark Vyas | 39m |
Accenture’s Artemis combines neural networks for real‑time predator detection with NLP on Yelp and RubMap reviews, license and adverse‑filing data to produce a… | ||
| Overcoming data infrastructure limitations with a new paradigm for ML | Davor Bonaci, Ryan Michael | 40m |
Kaskada describes a system that processes events chronologically and partitions by entity (user, age, show) to compute feature streams as of each event… | ||
| Has web data become part of today's core business fabric | Omri Orgad | 32m |
Claim: public web data now informs core business decisions with measurable uptake and concrete use cases. Cited survey shows 95% of financial services rely on… | ||
| Building a Robust Fraud Detection System | Gasia Atashian, Gasia Alashian | 42m |
Streaming clickstream and profile data feed three classifiers — dynamic labeling, behavior-similarity and email-similarity — whose outputs are OR’ed to flag… | ||
| Columnar Storage + Python: Powering Modern Data Science and Analytics | Rob Hedgpeth | 42m |
Columnar storage here uses MariaDB ColumnStore with extent mapping and distributed column partitions to cut IO dramatically (example: a 1B-row aggregate reads… | ||
| Creating and operating ML models from event based data using feature stores | Davor Bonaci, Charna Parkey | 40m |
Claims that a feature engine with native time travel (Kaskada) lets teams compute historical feature values instantly, test different prediction and label… | ||
| Is a Ransomware Attack in your Future? How to Prevent an Attack | Don Malloy | 14m |
Claims that backups alone fail and that data must be protected from copying, erasing and encrypting; demonstrates DualAuth’s FilingBox storage layer that… | ||
| HyreCar Data Analytics: Pushing the Pedal to the Metal | Linda Liu | 25m |
Linda Liu, Director, Data Analytics, HyreCar
Data Analytics plays a critical role in a fast growing company like HyreCar. In this talk, we will share how we… | ||
| Big Data, Artificial Intelligence, Machine Learning | Sano Hijazi | 15m |
DataProdigy claims to automate BI report generation by converting plain-language requests into Big Data queries and returns tailored outputs (example: 32… | ||
| Empowering Employment for Women in Tech with Artificial Intelligence? | Ashutosh Garg | 12m |
Eightfold.ai trains models on over 1 billion career profiles to predict who can learn a skill versus who already has it, surface matches and explain why, and… | ||
| In-Database Machine Learning with Jupyter | Paige Roberts | 40m |
Shows a Jupyter + Python workflow that keeps data and compute inside an MPP analytical database using verticaPy to run joins, interpolation and training… | ||
| A Practical Guide to Robust Multi modal Machine Learning in Education | Zitao Liu | 37m |
Describes a multimodal pipeline that aligns word timestamps to audio, extracts word-level acoustic embeddings, and fuses them with text via temporal alignment… | ||
| How to reduce your SQL Database costs on Azure | Sulamita Dantas, Leonardo Fonseca | 18m |
Shows concrete cost moves for Azure SQL: use the portal Pricing tier blade, read the workload chart, and drop idle dev/QA instances instead of guessing… | ||
| Earn Revenue in DeFi, NFTs and Consensus Blockchain | Mariana Danilovic | 36m |
Clear revenue paths: staking and LP fees on Uniswap/Sushi, Uniswap v3 concentrated liquidity mechanics for better yields, and yield farming that layers LP… | ||
| Data Challenges & Opportunities to Achieve Digital Equity | Jagjit Dhaliwal, Jeanne Holm, Dr. Steven J. Steinberg, Tom Mullen | 58m |
Counties and cities map needs and build infrastructure near homes, launch device drives and training, and measure outcomes; actions include distributing 18,000… | ||
| The Zero-Party Data Advantage: Connecting Opinions and Outcomes | Howard Ming | 26m |
Defines zero-party observed data as survey answers plus intentionally shared behavioral tracking, and claims a 100% zero-party panel with no third-party… | ||
| The Future of Language Models | Ash Pahwa | 40m |
Survey of current LMs: transformer-based models such as GPT-1/2/3 and BERT and Google’s LaMDA demo with Pluto and paper plane power chatbots and autocomplete… | ||
| How AI is changing CFOs world | Rafi Wadan | 41m |
Stargazr is a cloud planning/analytics tool for manufacturing that claims to find operational bottlenecks and save millions by cutting month-end reporting from… | ||
| Codeless Pipelines With Pulsar and Flink | Timothy J Spann | 39m |
Live demo shows Apache Pulsar ingesting MQTT and Kafka messages from an IoT device into topics, NiFi processors consuming and transforming JSON without code… | ||
| The Purposeful Innovator | Carnellia Ajasin | 22m |
A framework emerges from an ethical crisis at a consultancy into three actionable phases: strategy phase (validate problem and target user needs), roadmap… | ||
| End-to-End File Encryption in Browser with Open Source Penumbra | Mike Farrell | 25m |
An open source library called Penumbra implements end-to-end browser encryption that decrypts large files in the client without buffering whole files or… | ||
| Data Lake House in the Cloud: The Azure Solutions | Dennes Oliveira | 40m |
Claim: a single Azure environment replaces separate lake and warehouse by combining storage, MPP SQL, serverless SQL and Spark for ingestion, transformation… | ||
| Reigniting the ETL vs. ELT Debate - Which Better Supports the Business? | Craig Stewart | 38m |
Argues that cloud data warehouses change the ETL vs ELT choice: traditional ETL routes all bits through a beefy transform server while ELT loads fast into… | ||
| MySQL Indexes and Histograms to Speed Up Your Queries | David Stokes | 35m |
Shows how to use MySQL indexes, clustered primary keys, and histograms to give the optimizer real numbers instead of bad guesses — e.g., adding a multi-column… | ||
| Better, Faster, Stronger Streaming: Your First Dive into Flink SQL | Caito Scherr | 39m |
Uses Apache Flink SQL to build a real, scalable stream pipeline from local CSV or synthetic data in three steps (four if persisting results): untar Flink… | ||
| Zero Bias AI | Pramod Kunju | 35m |
Claim: machine learning reproduces systemic prejudice because models learn from historical records, so tools like facial recognition, mortgage-scoring models… | ||
| To B or Not To B : How Can Early Career Women Find Belonging at Work? | Sreyoshi Bhaduri, Tahsin Chowdhury | 23m |
NSF-funded longitudinal study uses weekly surveys (first 12 weeks) plus semi-structured interviews at 3, 6, 12 months and finds men report higher preparedness… | ||
| Pandemic Generosity: What Donation and Health Data Can Teach Us | Jared Sheehan, Tim Sarrantonio | 40m |
Combining public COVID datasets (Johns Hopkins, state dashboards) with 1.7 million+ donor records the presenters model pandemic scenarios and test real giving… | ||
| How To Make Yourself Visible While Working From Home | Claudia T Miller | 37m |
Offers concrete tactics: claims clients land roles in 90 days or less and secure up to $100,000 raises; cites stats—85% of roles filled via networking, 70%… | ||
| Moving People with Data | Jenny Rankin | 20m |
Shows that selective displays + narrative beat raw charts: the 1854 Broad Street pump map pinpoints cholera and removing the pump stops the epidemic; Gen Z… | ||
| How to Break into Business Intelligence & Data Analytics | Christian Bourdeau | 26m |
Concrete steps and outcomes: learn Excel, SQL, Python and Tableau, build an S3 → Redshift → Tableau pipeline and use Git/GitHub and Airflow for automation… | ||
| Talk to Your Data: Query Your Data Lake with Amazon QuickSight Q | Ginni Malik, Ying Wang | 39m |
Amazon QuickSight Q runs ML-powered natural language queries over uploaded datasets and AWS sources, demonstrated by building an Olympics topic from CSVs… | ||
| Lie factor and it's impact on visualisation | Sayantika Banik | 26m |
Defines lie factor = visualization effect / data effect and shows a recreated Gapminder in Tableau (x fertility, y life expectancy, color = continent, size =… | ||
| Detecting fake reviews at scale using Apache Spark and John Snow Labs | Debu Sinha | 43m |
End-to-end NLP pipeline claims to detect fake reviews at scale by ingesting ~1,600 labeled hotel reviews, converting raw text into Delta tables, running Spark… | ||
| Building scalable end-to-end deep learning pipelines in the cloud | Rustem Feyzkhanov | 40m |
Describes a concrete pipeline pattern that uses AWS Batch, AWS Fargate, Amazon SageMaker, AWS Lambda, AWS Step Functions where Step Functions orchestrates five… | ||
| Advanced Data Analytics and ML using Logical Data Fabric | Nishtha Chouhan | 33m |
Claims that a Denodo logical data fabric uses data virtualization to create a middle layer that integrates Snowflake, Oracle, Salesforce, CSV and log files… | ||
| Using Apache Cassandra as your Document Database | Daniel Farrell | 33m |
Argues Apache Cassandra can act as a document database by pairing Cassandra with Stargate and the Kubernetes distribution Kat Sandra to expose an automatically… | ||
| nothing matches | ||